A financial data processing method, device and equipment and a storage medium thereof

Abstract

This application belongs to the field of supply chain management technology and is applied to business and financial data processing scenarios. It relates to a financial data processing method, apparatus, device, and storage medium. The method involves: acquiring target data to be verified; adding a first distinguishing mark to data in the target data that meets the target addition requirements; template-based organization of all target data with the first distinguishing mark; identifying all data in the target data with the first distinguishing mark that meets reimbursement requirements and adding a second distinguishing mark; generating business invoices for all target data with the second distinguishing mark using a preset invoice generation template; and distributing all the finally generated business invoices to the corresponding receiving ends. Applying the financial data processing method described in this application to a supply chain system with complex billing data facilitates efficient and comprehensive management of business and financial data at the business and financial integration level.

Description

Technical Field

[0001] This application relates to the field of supply chain management technology and is applied in business and financial data processing scenarios, particularly to a financial data processing method, apparatus, equipment and its storage medium. Background Technology

[0002] With the promotion of online procurement and the popularization of online suppliers such as e-commerce, online business travel, and supplier-built e-commerce, online procurement is becoming increasingly common, business types are also increasing, and the format of supply and procurement invoices is becoming more and more complex, leading to difficulties in processing and managing supply chain business systems.

[0003] Currently, the increasingly complex formats of supply chain invoices necessitate that supply chain management service providers design different data recognition plugins for different invoices, increasing their workload. Furthermore, the complex invoice formats and data recognition plugins hinder efficient integrated management of business and financial data at the business and financial levels, further complicating this aspect of management. Therefore, there is an urgent need for a financial data processing method to achieve efficient integrated management of complex supply chain business and invoice data at the business and financial levels. Summary of the Invention

[0004] The purpose of this application is to provide a financial data processing method, apparatus, device and storage medium, so as to achieve efficient comprehensive management of complex supply chain business data and billing data at the business and financial level.

[0005] To address the aforementioned technical problems, this application provides a financial data processing method, employing the following technical solution:

[0006] A financial data processing method includes the following steps:

[0007] Obtain the target data to be verified, wherein the target data includes billing data;

[0008] According to the preset tagging strategy, a first distinguishing tag is added to the data in the target data to be checked that meets the target tagging requirements;

[0009] Based on the preset data processing template, all target data to be checked that have been marked with the first distinguishing mark are processed to obtain the templated processing results corresponding to all the data marked with the first distinguishing mark.

[0010] According to the preset reimbursement identification strategy, the reimbursement judgment fields corresponding to all first distinguishing marker data are extracted from all templated sorting results, wherein the reimbursement identification strategy is provided by the target financial management end;

[0011] Based on the reimbursement determination field, identify all data in the target data to be verified that meets the reimbursement requirements and add the first differentiation mark, and then perform the second differentiation mark;

[0012] Based on the preset invoice generation template, business invoices are generated for all target data to be verified that have been marked with the second distinction mark.

[0013] According to the preset distribution strategy, all the business tickets generated in the end will be distributed to the corresponding receiving end.

[0014] Furthermore, the step of obtaining the target data to be verified specifically includes:

[0015] Based on the SOA integration service architecture provided by the target verification business system, the target data to be verified is obtained from multiple data sources. The SOA integration service architecture supports SSO single point integration, interface integration, ETL data mart integration and Web service integration.

[0016] The process of obtaining the target data to be verified from multiple data sources includes:

[0017] By combining RESTful API calls, the target data to be verified is obtained synchronously from multiple data sources.

[0018] Utilize message queues to asynchronously retrieve target data to be verified from multiple data sources.

[0019] Furthermore, the step of adding a first distinguishing marker to the data in the target data to be verified that meets the target addition requirements according to a preset marker addition strategy specifically includes:

[0020] Retrieve supply and demand business record logs from the business monitoring component of the target supply chain system to determine whether the generation of the target data to be verified conforms to the preset business logic rules;

[0021] If the generation of the target data to be verified conforms to the preset business logic rules, then a confirmation pass mark, i.e. the first distinction mark, is added to the target data to be verified;

[0022] If the generation of the target data to be verified does not conform to the preset business logic rules, a prompt indicating that the target data to be verified has been generated incorrectly will be sent to the target monitoring terminal.

[0023] Furthermore, before performing the step of organizing all the target data to be checked that has been marked with a first distinguishing tag according to a preset data organizing template, and obtaining the templated organizing results corresponding to all the data with the first distinguishing tag, the method further includes:

[0024] Based on all the supply and demand relationships involved in the target supply chain system, create corresponding data processing templates, with different data processing templates corresponding to different supply and demand relationships;

[0025] Obtain the data processing templates corresponding to all supply and demand relationships as the preset data processing templates;

[0026] The preset data processing template is deployed into the preset text content extraction model;

[0027] The preset text content extraction model is automatically trained using pre-constructed training samples to obtain an automatically trained text content extraction model. The training samples include target data to be verified, which are simulated and generated based on all the supply and demand relationships.

[0028] Furthermore, the step of organizing all the target data to be checked that has been marked with a first distinguishing tag according to a preset data organizing template, and obtaining the templated organizing results corresponding to all the data with the first distinguishing tag, specifically includes:

[0029] All target data to be verified that have been marked with the first distinguishing marker are input into the text content extraction model that has been trained by the automated extraction process;

[0030] The text content recognition component in the text content extraction model identifies the data processing templates corresponding to all target data to be verified that have been marked with the first distinguishing marker.

[0031] The text content extraction component in the text content extraction model extracts text content from all target data to be checked that have been marked with the first distinguishing marker, and fills the text content extraction results into the corresponding data processing template.

[0032] Obtain the templated processing results corresponding to all the first distinguishing marker data output by the text content extraction model.

[0033] Furthermore, the preset reimbursement identification strategy includes a first identification strategy, a second identification strategy, a third identification strategy, and a fourth identification strategy. The reimbursement determination field includes a first determination field, a second determination field, a third determination field, and a fourth determination field. Before performing the step of extracting the reimbursement determination fields corresponding to all first distinguishing marker data from all templated processing results according to the preset reimbursement identification strategy, the method further includes:

[0034] An automated judgment model is generated based on the first, second, third, and fourth identification strategies. The first identification strategy specifies a first judgment field, used to identify whether the corresponding first distinguishing marker data conforms to the proposed business budget range. The second identification strategy specifies a second judgment field, used to identify whether the corresponding first distinguishing marker data conforms to the proposed expense usage standard. The third identification strategy specifies a third judgment field, used to identify whether the corresponding first distinguishing marker data conforms to the legally defined business scope. The fourth identification strategy specifies a fourth judgment field, used to identify whether the corresponding first distinguishing marker data conforms to the legally defined reimbursement business type.

[0035] The step of extracting the reimbursement determination fields corresponding to all first distinguishing marker data from all templated processing results according to a preset reimbursement identification strategy specifically includes:

[0036] According to the first identification strategy, the first determination field of all first distinguishing marker data is extracted from all templated sorting results;

[0037] According to the second identification strategy, the second determination field of all first distinguishing marker data is extracted from all templated sorting results;

[0038] According to the third identification strategy, the third determination field of all first distinguishing marker data is extracted from all templated sorting results;

[0039] According to the fourth identification strategy, the fourth determination field of all first distinguishing marker data is extracted from all templated sorting results.

[0040] Furthermore, the step of identifying all data in the target data to be verified that meets the reimbursement requirements based on the reimbursement determination field and performing a second differentiation mark specifically includes:

[0041] Input the reimbursement determination field into the automated determination model;

[0042] Based on the first identification strategy and the first determination field in the reimbursement determination field, it is determined whether the target data to be verified, which currently has a first distinguishing mark added, conforms to the proposed business budget range.

[0043] Based on the second identification strategy and the second determination field in the reimbursement determination field, it is determined whether the target data to be verified, which currently has a first distinguishing mark added, meets the proposed expense usage standards.

[0044] Based on the third identification strategy and the third determination field in the reimbursement determination field, it is determined whether the target data to be verified, which currently has a first distinguishing mark added, conforms to the legal business scope.

[0045] Based on the fourth identification strategy and the fourth determination field in the reimbursement determination field, it is determined whether the target data to be verified, which currently has the first distinguishing mark added, conforms to the legal reimbursement business type;

[0046] If the target data to be verified, which has been marked with the first distinguishing tag, simultaneously meets the proposed business budget range, the proposed expense usage standards, the legal business scope, and the legal reimbursement business type, then it is marked with the second distinguishing tag; otherwise, a message indicating that reimbursement is not permitted is sent to the target data source.

[0047] To address the aforementioned technical problems, this application also provides a financial data processing apparatus, which employs the following technical solution:

[0048] A financial data processing device, comprising:

[0049] The target data acquisition module is used to acquire target data to be verified, wherein the target data includes billing data;

[0050] The first distinguishing marker adding module is used to add a first distinguishing marker to the data in the target data to be verified that meets the target adding requirements according to a preset marker adding strategy;

[0051] The template-based data processing module is used to process all target data to be checked that have been marked with the first distinguishing marker according to a preset data processing template, and to obtain the template-based processing results corresponding to all data with the first distinguishing marker.

[0052] The reimbursement determination field extraction module is used to extract the reimbursement determination fields corresponding to all first distinguishing marker data from all templated sorting results according to a preset reimbursement identification strategy, wherein the reimbursement identification strategy is provided by the target financial management end;

[0053] The second differentiation marking module is used to identify all data in the target data to be checked that meets the reimbursement requirements based on the reimbursement determination field, and to perform the second differentiation marking.

[0054] The business invoice generation module is used to generate business invoices for all target data to be verified that have been marked with a second distinction, in conjunction with a preset invoice generation template.

[0055] The business ticket distribution module is used to distribute all the final generated business tickets to the corresponding receiving end according to the preset distribution strategy.

[0056] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution:

[0057] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the financial data processing method described above.

[0058] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below:

[0059] A computer-readable storage medium storing computer-readable instructions, which, when executed by a processor, implement the steps of the financial data processing method described above.

[0060] Compared with the prior art, the embodiments of this application have the following main advantages:

[0061] The financial data processing method described in this application involves: acquiring target data to be verified; adding a first distinguishing mark to data in the target data that meets the target addition requirements; template-forming all target data with the first distinguishing mark; identifying all data in the target data with the first distinguishing mark that meets the reimbursement requirements and adding a second distinguishing mark; generating business invoices for all target data with the second distinguishing mark using a preset invoice generation template; and distributing all the finally generated business invoices to the corresponding receiving end. This financial data processing method can be applied to supply chain business systems with complex billing data and numerous subsystems, enabling management service departments to efficiently manage complex supply chain business data and billing data at both the business and financial levels. Attached Figure Description

[0062] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 This is an exemplary system architecture diagram to which this application can be applied;

[0064] Figure 2 This is a flowchart of one embodiment of the financial data processing method according to this application;

[0065] Figure 3 yes Figure 2 A flowchart of a specific embodiment of step 202 shown;

[0066] Figure 4 This is a flowchart of a specific embodiment of the automated processing training performed before template-based data processing in the financial data processing method described in this application;

[0067] Figure 5 yes Figure 2 A flowchart of a specific embodiment of step 203 shown;

[0068] Figure 6 yes Figure 2 A flowchart of a specific embodiment of step 206 shown;

[0069] Figure 7 This is a schematic diagram of the structure of one embodiment of the financial data processing apparatus according to this application;

[0070] Figure 8 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0071] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0072] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0073] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0074] like Figure 1As shown, system architecture 100 may include terminal device 101, network 102, and server 103. Terminal device 101 may be a laptop 1011, tablet 1012, or mobile phone 1013. Network 102 is used as a medium to provide a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables.

[0075] Users can use terminal device 101 to interact with server 103 via network 102 to receive or send messages, etc. Various communication client applications can be installed on terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0076] Terminal device 101 can be various electronic devices with a display screen and support web browsing. In addition to laptops 1011, tablets 1012, or mobile phones 1013, terminal device 101 can also be e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 players (Moving Picture Experts Group Audio Layer IV), laptops, and desktop computers.

[0077] Server 103 can be a server that provides various services, such as a backend server that provides support for the pages displayed on terminal device 101.

[0078] It should be noted that the financial data processing method provided in this application embodiment is generally executed by a server, and correspondingly, the financial data processing device is generally located in the server.

[0079] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0080] Continue to refer to Figure 2 A flowchart of an embodiment of the financial data processing method according to this application is shown. The financial data processing method includes the following steps:

[0081] Step 201: Obtain the target data to be verified, wherein the target data includes billing data.

[0082] Specifically, the billing data includes bill ID, bill dimension, amount payable, tax rate, amount excluding tax, invoice type, and other fields. The bill dimension refers to the specific business and financial attribution of the bill, generally including the original order number, sub-order number, business type code, purchasing department code, purchasing company code, expense control department code, and accounting entity code. Other fields refer to reference information for user confirmation, such as product name, product category, and recipient address. The financial data processing method described in this application is applied to supply chain business systems with complex billing data and numerous subsystems, facilitating efficient and comprehensive management of complex supply chain business data and billing data by management or service departments.

[0083] Step 202: According to the preset tag addition strategy, add a first distinguishing tag to the data in the target data to be verified that meets the target addition requirements.

[0084] In this embodiment, a first distinguishing mark is added to the data in the target data to be verified that meets the target addition requirements. It should be understood that all the target data to be verified obtained in step 201, that is, each target data to be verified, is unmarked data. In step 202, the target addition requirements specify what kind of data to add the first distinguishing mark, and the preset mark addition strategy specifies the mark format of the first distinguishing mark.

[0085] Specifically, for example, the target addition requirement is to perform a first distinguishing mark on data that is correctly recorded in the business execution or supply business of the supply chain business.

[0086] By adding a first distinguishing marker, the data to be processed can be identified in subsequent processing steps. Data that has not been marked with the first distinguishing marker may be data that has not yet been checked by the business process, or it may be data that has been checked by the business process but may be questionable. For these two types of data, no further processing will be performed.

[0087] Step 203: Based on the preset data processing template, process all target data to be checked that have been marked with the first distinguishing mark, and obtain the templated processing results corresponding to all the data marked with the first distinguishing mark.

[0088] Specifically, all the target data to be verified that has been marked with the first distinguishing marker refers to all data that has been checked and passed at the business level. For such data, a preset data processing template is used for template processing to facilitate data management and subsequent calls.

[0089] In this embodiment, the preset data processing template can be set according to the specific data processing template of the actual supply chain business system.

[0090] Step 204: Based on the preset reimbursement identification strategy, extract the reimbursement judgment fields corresponding to all the first distinguishing marker data from all the templated sorting results, wherein the reimbursement identification strategy is provided by the target financial management terminal.

[0091] Specifically, since the financial management end knows best which bill data is eligible for reimbursement, the reimbursement judgment fields corresponding to all the first distinguishing data are extracted from all the templated results based on the reimbursement identification strategy provided by the target financial management end, so as to quickly identify and determine the reimbursable bill data.

[0092] In this embodiment, the preset reimbursement identification strategy is provided by the target financial management terminal; the reimbursement judgment field is also set by the target financial management terminal. Specifically, the reimbursement judgment field may include, for example, the business name, business type, reimbursement expense, name and type of purchased goods, etc.

[0093] Step 205: Based on the reimbursement determination field, identify all data in the target data to be verified that meets the reimbursement requirements and add the first differentiation mark, and then perform the second differentiation mark.

[0094] Specifically, after business-level verification and template-based organization, business invoice data is used to identify and mark reimbursement compliance through a reimbursement judgment field. For target data awaiting verification that meets reimbursement requirements (i.e., invoice data), a second distinguishing mark is applied; for target data awaiting verification that does not meet reimbursement requirements, it can be cached for later statistical analysis, or a message indicating non-compliance and non-reimbursement can be sent to the target data source.

[0095] This embodiment combines business-level and financial-level data processing, enabling rapid identification of invoices that meet financial reimbursement requirements arising from supply chain operations. This facilitates quick filtering of reimbursable invoices by business managers and streamlines reimbursement management between business and finance departments.

[0096] In this embodiment, the first distinguishing marker and the second distinguishing marker may have different formats or use different marker characters.

[0097] Step 206: Based on the preset invoice generation template, generate business invoices for all target data to be verified that have been marked with the second distinction mark.

[0098] In this embodiment, the preset invoice generation template can be a unified format invoice generation template provided by the service support provider in the supply chain business system. In order to facilitate the unified processing of invoices for different supply sub-businesses, the invoice generation template provided by the tax authority can be preferred for generating business invoices, which facilitates subsequent billing and management.

[0099] Step 207: Distribute all the final generated business tickets to the corresponding receiving end according to the preset distribution strategy.

[0100] Specifically, a business invoice is generated for the billing data corresponding to a complete supply and demand transaction process. At the very least, the business invoice should be sent to the receiving end of both parties to the billing transaction, such as the business management end and the financial management end. Of course, it should also be sent to the service support end that provides supply chain business services, so that the supply chain business service provider can supervise and verify the transaction data.

[0101] In this embodiment, the following steps are taken: First, target data to be verified is acquired; a first distinguishing marker is added to data in the target data that meets the target addition requirements; all target data with the first distinguishing marker is templated and organized; all data in the target data with the first distinguishing marker that meets the reimbursement requirements is identified and marked with a second distinguishing marker; business invoices are generated for all target data with the second distinguishing marker, using a preset invoice generation template; and finally, all generated business invoices are distributed to the corresponding receiving terminals. This financial data processing method is applied to supply chain business systems with complex billing data and numerous subsystems, enabling management service departments to efficiently manage complex supply chain business data and billing data at both the business and financial levels.

[0102] In this embodiment, the step of obtaining the target data to be verified specifically includes: obtaining the target data to be verified from multiple data sources based on the SOA integration service architecture provided by the target verification business system, wherein the SOA integration service architecture supports SSO single-point integration, interface integration, ETL data mart integration and Web service integration.

[0103] Specifically, the target verification business system can be a verification subsystem within the supply chain business system. This verification subsystem supports acquiring target data to be verified from multiple data sources. Furthermore, it possesses an SOA (Service-Oriented Architecture) integration service architecture, supporting SSO (Single Sign-On) integration, interface integration, ETL (Extract-Transform-Load) data mart integration, and Web service integration, facilitating subsequent acquisition of the target data to be verified from different integration modules.

[0104] Specifically, obtaining the target data to be verified from the multi-source data source includes: obtaining the target data to be verified from the multi-source data source in a synchronous manner by combining RESTful API calls, and obtaining the target data to be verified from the multi-source data source in an asynchronous manner by utilizing a message queue.

[0105] In this embodiment, the acquisition of target data to be verified supports both synchronous and asynchronous acquisition. The multi-source data end includes multiple different product suppliers in the target supply chain business system, as well as multiple product procurement ends with the target supply chain business system as the procurement system.

[0106] Continue to refer to Figure 3 , Figure 3 yes Figure 2 A flowchart of a specific embodiment of step 202 shown includes the following steps:

[0107] Step 301: Retrieve supply and demand business record logs from the business monitoring component of the target supply chain system to determine whether the generation of the target data to be verified conforms to the preset business logic rules;

[0108] Specifically, based on the supply and demand business record logs, an automatic business process walkthrough can be performed. The supply and demand business record logs can be retrieved from the business monitoring component of the target supply chain system to determine whether the generation of the target data to be verified conforms to the preset business logic rules. The supply and demand business record logs are generally recorded and provided by the business monitoring component of the target supply chain business system.

[0109] Step 302: If the generation of the target data to be verified conforms to the preset business logic rules, then add a confirmation pass mark to the target data to be verified, namely the first difference mark;

[0110] Step 303: If the generation of the target data to be verified does not conform to the preset business logic rules, a prompt indicating that the target data to be verified has been generated is sent to the target monitoring terminal.

[0111] Specifically, for example: before the obtained billing data is templated, the accuracy of the generated or recorded billing data is verified based on the supply and demand order purchase situation involved in the generation of the billing data. If correct, confirmation is added; otherwise, an error message regarding the generation of supply and demand billing data is sent. This involves retrieving supply and demand business record logs from the business monitoring component of the target supply chain system, thus enabling a business-level verification check of the target data to be verified before generating business and financial invoices. Data that passes the check is marked with a first distinction tag for subsequent processing, while data that fails the check or has not yet been checked is not marked with a first distinction tag for easy identification by the processing unit during subsequent processing.

[0112] Continue to refer to Figure 4 In some optional implementations, an automated processing training step is included before step 203, prior to template preparation. Figure 4 This is a flowchart of a specific embodiment of the automated processing training before template-based data processing in the financial data processing method described in this application, including the following steps:

[0113] Step 401: Create corresponding data processing templates for all supply and demand relationships involved in the target supply chain system. Different supply and demand relationships correspond to different data processing templates.

[0114] Specifically, based on all the supply and demand relationships involved in the target supply chain system, corresponding data processing templates are created. For example, different data processing templates are created based on different supply and demand businesses, different supply and demand companies, different supply and demand departments, and different supply and demand types.

[0115] Step 402: Obtain the data processing templates corresponding to all supply and demand relationships as the preset data processing templates;

[0116] Step 403: Deploy the preset data processing template into the preset text content extraction model;

[0117] Step 404: Use the pre-constructed training samples to automatically extract and train the preset text content extraction model to obtain the automatically trained text content extraction model. The training samples include target data to be verified, which are simulated and generated based on all the supply and demand relationships.

[0118] By combining the data processing template and the simulated target data to be verified, a text content extraction model for automated extraction is trained. This allows for subsequent use of the model to automatically extract text content from the actual target data to be verified, i.e., to all target data to be verified with the first distinguishing marker, and to automatically process the text content using templates. This improves the efficiency of template processing and makes the process more automated and intelligent.

[0119] Continue to refer to Figure 5 , Figure 5 yes Figure 2 A flowchart of a specific embodiment of step 203 shown includes the following steps:

[0120] Step 501: Input all the target data to be checked with the first distinguishing marker added into the text content extraction model that has been trained by the automated extraction;

[0121] Step 502: Using the text content recognition component in the text content extraction model, identify the data processing templates corresponding to all the target data to be verified that have been marked with the first distinguishing marker.

[0122] Specifically, the text content recognition component in the text content extraction model can be a text content recognition component based on OCR optical recognition technology.

[0123] First, based on the text content recognition component in the text content extraction model, all specific data content contained in the target data to be verified that has been marked with the first distinguishing mark is identified. Then, based on the data content that can be processed according to different data processing templates, the data processing templates corresponding to the target data to be verified that have been marked with the first distinguishing mark are selected.

[0124] Alternatively, the text content recognition component in the text content extraction model can be used to identify the supply and demand relationships contained in all target data to be verified that have been marked with the first distinguishing marker. Based on the data processing templates corresponding to different supply and demand relationships, the data processing templates corresponding to all target data to be verified that have been marked with the first distinguishing marker can be selected.

[0125] Here, the specific data content of the target data to be verified includes a pre-defined identification field used to characterize the relationship between the data processing template and the target data to be verified. The corresponding data processing template is determined through the identification field.

[0126] Step 503: Extract text content from all target data to be checked that have been marked with the first distinguishing marker using the text content extraction component in the text content extraction model, and fill the text content extraction results into the corresponding data processing template.

[0127] Specifically, the text content extraction component in the text content extraction model can be a text content extraction component based on the Transformer codec structure. Through the text content extraction component, it is possible to accurately extract the text content from the target data to be verified, and directly use the decoder in the Transformer codec structure to output the extracted text content and fill it into the corresponding data processing template.

[0128] Step 504: Obtain the templated processing results corresponding to all the first distinguishing marker data output by the text content extraction model.

[0129] By adopting a model-based processing approach, the actual target data to be verified, namely all target data to be verified with the first distinguishing marker, is automatically extracted and templated, which improves the efficiency of template processing and makes it more automated and intelligent.

[0130] In this embodiment, the preset reimbursement identification strategy includes a first identification strategy, a second identification strategy, a third identification strategy, and a fourth identification strategy, and the reimbursement determination field includes a first determination field, a second determination field, a third determination field, and a fourth determination field.

[0131] In this embodiment, before performing the step of extracting the reimbursement judgment fields corresponding to all first distinguishing marker data from all templated sorting results according to the preset reimbursement identification strategy, the method further includes: generating an automated judgment model according to the first identification strategy, the second identification strategy, the third identification strategy, and the fourth identification strategy. The first identification strategy specifies a first judgment field, which is used to identify whether the corresponding first distinguishing marker data conforms to the proposed business budget range. The second identification strategy specifies a second judgment field, which is used to identify whether the corresponding first distinguishing marker data conforms to the proposed expense usage standard. The third identification strategy specifies a third judgment field, which is used to identify whether the corresponding first distinguishing marker data conforms to the legally defined business scope. The fourth identification strategy specifies a fourth judgment field, which is used to identify whether the corresponding first distinguishing marker data conforms to the legally defined reimbursement business type.

[0132] By pre-setting a first judgment field, a second judgment field, a third judgment field, and a fourth judgment field, and by setting a first identification strategy, a second identification strategy, a third identification strategy, and a fourth identification strategy based on the first judgment field, the system can subsequently filter out reimbursable bill data that meets the proposed business budget range, the proposed expense usage standards, the legal business scope, and the legal reimbursement business type, thus identifying the target data to be processed for reimbursement.

[0133] In this embodiment, the step of extracting the reimbursement determination fields corresponding to all first distinguishing marker data from all templated processing results according to a preset reimbursement identification strategy specifically includes: extracting the first determination field of all first distinguishing marker data from all templated processing results according to the first identification strategy; extracting the second determination field of all first distinguishing marker data from all templated processing results according to the second identification strategy; extracting the third determination field of all first distinguishing marker data from all templated processing results according to the third identification strategy; and extracting the fourth determination field of all first distinguishing marker data from all templated processing results according to the fourth identification strategy.

[0134] In this embodiment, the step of identifying all data in the target data to be verified that meets the reimbursement requirements and has been marked with a first distinction tag based on the reimbursement determination field, and then performing a second distinction tag, specifically includes: inputting the reimbursement determination field into the automated determination model, specifically, inputting the first determination field, the second determination field, the third determination field, and the fourth determination field into the automated determination model; identifying whether the target data to be verified that has been marked with a first distinction tag conforms to the proposed business budget range according to the first identification strategy and the first determination field in the reimbursement determination field; and identifying whether the target data to be verified that has been marked with a first distinction tag conforms to the proposed business budget range according to the second identification strategy and the second determination field in the reimbursement determination field. Verify whether the target data meets the proposed expense usage standards; identify whether the target data currently marked with the first differentiation tag conforms to the legal business scope according to the third identification strategy and the third determination field in the reimbursement determination field; identify whether the target data currently marked with the first differentiation tag conforms to the legal reimbursement business type according to the fourth identification strategy and the fourth determination field in the reimbursement determination field; if the target data currently marked with the first differentiation tag conforms to the proposed business budget range, the proposed expense usage standards, the legal business scope, and the legal reimbursement business type, then mark it with the second differentiation tag; otherwise, send a message indicating non-reimbursement to the target data source.

[0135] Using the first, second, third, and fourth determination fields, as well as the first, second, third, and fourth identification strategies, business bill data eligible for reimbursement is filtered out and marked with a second distinguishing mark to facilitate the generation of relevant business and financial invoices from the reimbursable business bill data.

[0136] In this embodiment, the preset invoice generation template includes invoice generation templates provided by tax authorities.

[0137] Continue to refer to Figure 6 , Figure 6 yes Figure 2 A flowchart of a specific embodiment of step 206 shown includes the following steps:

[0138] Step 601: Obtain each target data item to be verified that has been marked with the second distinguishing tag;

[0139] Step 602: Extract specific data content from all target data to be verified that have been marked with the second distinction tag, and obtain the data content extraction results;

[0140] Specifically, the step of extracting specific data content from all target data to be verified that has been marked with the second distinction to obtain data content extraction results includes: extracting fill data content from all target data to be verified that has been marked with the second distinction based on the fill items in the invoice generation template provided by the tax authority, and obtaining fill data content extraction results.

[0141] Step 603: Map the extracted data content to the invoice generation template provided by the tax authority to generate business invoices.

[0142] By using the invoice generation templates provided by the tax authorities to generate business invoices, the problem of complex business invoice types caused by each business service provider generating invoices separately is avoided, which facilitates subsequent billing and management.

[0143] In this embodiment, the receiving end includes a business management end and a financial management end, as well as a supply chain business service supervision end.

[0144] Specifically, the step of distributing all the final generated business invoices to the corresponding receiving end according to the preset distribution strategy includes: sending the final generated business invoices to the corresponding business management end according to the business identification information, and sending the final generated business invoices to the corresponding financial management end according to the company identification information.

[0145] This application integrates business management and financial management at both levels, generating the same business invoices for both business and financial management. This facilitates joint business and financial management as well as subsequent financial verification.

[0146] In this embodiment, the steps of acquiring the target data to be verified, generating business invoices, and distributing all the finally generated business invoices to the corresponding receiving end can be accomplished by combining timers or triggers to achieve timed or triggered processing, making it more automated.

[0147] This application involves: acquiring target data to be verified; adding a first distinguishing mark to data in the target data that meets the target addition requirements; template-forming all target data with the first distinguishing mark; identifying all data in the target data with the first distinguishing mark that meets the reimbursement requirements and adding a second distinguishing mark; generating business invoices for all target data with the second distinguishing mark using a preset invoice generation template; and distributing all the finally generated business invoices to the corresponding receiving end. This financial data processing method can be applied to supply chain business systems with complex billing data and numerous subsystems, enabling management service departments to efficiently manage complex supply chain business data and billing data at both the business and financial levels.

[0148] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0149] The fundamental technologies of artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0150] In this embodiment, the following steps are taken: First, target data to be verified is acquired; a first distinguishing marker is added to data in the target data that meets the target addition requirements; all target data with the first distinguishing marker is templated and organized; all data in the target data with the first distinguishing marker that meets the reimbursement requirements is identified and marked with a second distinguishing marker; business invoices are generated for all target data with the second distinguishing marker in combination with a preset invoice generation template; and all generated business invoices are distributed to the corresponding receiving end. This financial data processing method can be applied to supply chain business systems with complex billing data and numerous subsystems, enabling management service departments to efficiently manage complex supply chain business data and billing data at both the business and financial levels.

[0151] Further reference Figure 7 As a response to the above Figure 2 To implement the method shown, this application provides an embodiment of a financial data processing apparatus, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0152] like Figure 7 As shown, the financial data processing device 700 described in this embodiment includes: a target data acquisition module 701, a first distinguishing marker addition module 702, a template organization module 703, a reimbursement judgment field extraction module 704, a second distinguishing marker module 705, a business invoice generation module 706, and a business invoice distribution module 707. Wherein:

[0153] The target data acquisition module 701 is used to acquire target data to be verified, wherein the target data includes billing data;

[0154] The first distinguishing marker adding module 702 is used to add a first distinguishing marker to the data in the target data to be verified that meets the target adding requirements according to a preset marker adding strategy;

[0155] The template-based data processing module 703 is used to process all target data to be checked that have been marked with the first distinguishing mark according to the preset data processing template, and to obtain the template-based processing results corresponding to all data with the first distinguishing mark.

[0156] The reimbursement determination field extraction module 704 is used to extract the reimbursement determination fields corresponding to all first distinguishing marker data from all templated sorting results according to a preset reimbursement identification strategy, wherein the reimbursement identification strategy is provided by the target financial management end;

[0157] The second differentiation marking module 705 is used to identify all data in the target data to be checked that meets the reimbursement requirements based on the reimbursement determination field and to perform the second differentiation marking.

[0158] The business invoice generation module 706 is used to generate business invoices for all target data to be verified that have been marked with the second distinction tag, in combination with the preset invoice generation template.

[0159] The business ticket distribution module 707 is used to distribute all the finally generated business tickets to the corresponding receiving end according to the preset distribution strategy.

[0160] This application involves: acquiring target data to be verified; adding a first distinguishing mark to data in the target data that meets the target addition requirements; template-forming all target data with the first distinguishing mark; identifying all data in the target data with the first distinguishing mark that meets the reimbursement requirements and adding a second distinguishing mark; generating business invoices for all target data with the second distinguishing mark using a preset invoice generation template; and distributing all the finally generated business invoices to the corresponding receiving end. This financial data processing method can be applied to supply chain business systems with complex billing data and numerous subsystems, enabling management service departments to efficiently manage complex supply chain business data and billing data at both the business and financial levels.

[0161] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0162] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0163] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed] for details. Figure 8 , Figure 8 This is a basic structural block diagram of the computer device in this embodiment.

[0164] The computer device 8 includes a memory 8a, a processor 8b, and a network interface 8c, which are interconnected via a system bus. It should be noted that... Figure 8 Only a computer device 8 with component memory 8a, processor 8b, and network interface 8c is shown. However, it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Those skilled in the art will understand that the computer device described herein is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0165] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0166] The memory 8a includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 8a may be an internal storage unit of the computer device 8, such as the hard disk or memory of the computer device 8. In other embodiments, the memory 8a may also be an external storage device of the computer device 8, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 8. Of course, the memory 8a may include both the internal storage unit and its external storage device of the computer device 8. In this embodiment, the memory 8a is typically used to store the operating system and various application software installed on the computer device 8, such as computer-readable instructions for a financial data processing method. In addition, the memory 8a can also be used to temporarily store various types of data that have been output or will be output.

[0167] In some embodiments, the processor 8b may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other financial data processing chip. The processor 8b is typically used to control the overall operation of the computer device 8. In this embodiment, the processor 8b is used to execute computer-readable instructions stored in the memory 8a or to process data, for example, to execute computer-readable instructions for the financial data processing method.

[0168] The network interface 8c may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 8 and other electronic devices.

[0169] The computer equipment proposed in this embodiment belongs to the field of supply chain management technology and is applied in business and financial data processing scenarios. This application acquires target data to be verified; adds a first distinguishing mark to data in the target data that meets the target addition requirements; templates all target data with the first distinguishing mark; identifies all data in the target data with the first distinguishing mark that meets the reimbursement requirements and adds a second distinguishing mark; combines a preset invoice generation template to generate business invoices for all target data with the second distinguishing mark; and distributes all the finally generated business invoices to the corresponding receiving end. Applying the financial data processing method described in this application to supply chain business systems with complex billing data and many subsystems involved enables management service departments to efficiently manage complex supply chain business data and billing data at the business and financial integration level.

[0170] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by a processor to cause the processor to perform the steps of the financial data processing method described above.

[0171] The computer-readable storage medium proposed in this embodiment belongs to the field of supply chain management technology and is applied in business and financial data processing scenarios. This application obtains target data to be verified; adds a first distinguishing mark to data in the target data that meets the target addition requirements; templates all target data with the first distinguishing mark; identifies all data in the target data with the first distinguishing mark that meets the reimbursement requirements and adds a second distinguishing mark; combines a preset invoice generation template to generate business invoices for all target data with the second distinguishing mark; and distributes all the finally generated business invoices to the corresponding receiving end. Applying the financial data processing method described in this application to supply chain business systems with complex billing data and many subsystems involved enables management service departments to efficiently manage complex supply chain business data and billing data at the business and financial integration level.

[0172] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0173] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A financial data processing method, characterized in that, Includes the following steps: Obtain the target data to be verified, wherein the target data includes billing data; According to the preset tagging strategy, a first distinguishing tag is added to the data in the target data to be checked that meets the target tagging requirements; Based on the preset data processing template, all target data to be checked that have been marked with the first distinguishing mark are processed to obtain the templated processing results corresponding to all the data marked with the first distinguishing mark. According to the preset reimbursement identification strategy, the reimbursement judgment fields corresponding to all first distinguishing marker data are extracted from all templated sorting results, wherein the reimbursement identification strategy is provided by the target financial management end; Based on the reimbursement determination field, identify all data in the target data to be verified that meets the reimbursement requirements and add the first differentiation mark, and then perform the second differentiation mark; Based on the preset invoice generation template, business invoices are generated for all target data to be verified that have been marked with the second distinction mark. According to the preset distribution strategy, all the business tickets generated in the end will be distributed to the corresponding receiving end.

2. The financial data processing method according to claim 1, characterized in that, The step of obtaining the target data to be verified specifically includes: Based on the SOA integration service architecture provided by the target verification business system, the target data to be verified is obtained from multiple data sources. The SOA integration service architecture supports SSO single point integration, interface integration, ETL data mart integration and Web service integration. The process of obtaining the target data to be verified from multiple data sources includes: By combining RESTful API calls, the target data to be verified is obtained synchronously from multiple data sources. Utilize message queues to asynchronously retrieve target data to be verified from multiple data sources.

3. The financial data processing method according to claim 1, characterized in that, The step of adding a first distinguishing marker to the data in the target data to be verified that meets the target addition requirements according to a preset marker addition strategy specifically includes: Retrieve supply and demand business record logs from the business monitoring component of the target supply chain system to determine whether the generation of the target data to be verified conforms to the preset business logic rules; If the generation of the target data to be verified conforms to the preset business logic rules, then a confirmation pass mark, i.e. the first distinction mark, is added to the target data to be verified; If the generation of the target data to be verified does not conform to the preset business logic rules, a prompt indicating that the target data to be verified has been generated incorrectly will be sent to the target monitoring terminal.

4. The financial data processing method according to claim 1, characterized in that, Before performing the step of organizing all target data to be checked that have been marked with a first distinguishing tag according to a preset data organizing template, and obtaining the templated organizing results corresponding to all data with the first distinguishing tag, the method further includes: Based on all the supply and demand relationships involved in the target supply chain system, create corresponding data processing templates, with different data processing templates corresponding to different supply and demand relationships; Obtain the data processing templates corresponding to all supply and demand relationships as the preset data processing templates; The preset data processing template is deployed into the preset text content extraction model; The preset text content extraction model is automatically trained using pre-constructed training samples to obtain an automatically trained text content extraction model. The training samples include target data to be verified, which are simulated and generated based on all the supply and demand relationships.

5. The financial data processing method according to claim 4, characterized in that, The step of organizing all target data to be checked with added first distinguishing markers according to a preset data organizing template, and obtaining the templated organizing results corresponding to all data with first distinguishing markers, specifically includes: All target data to be verified that have been marked with the first distinguishing marker are input into the text content extraction model that has been trained by the automated extraction process; The text content recognition component in the text content extraction model identifies the data processing templates corresponding to all target data to be verified that have been marked with the first distinguishing marker. The text content extraction component in the text content extraction model extracts text content from all target data to be checked that have been marked with the first distinguishing marker, and fills the text content extraction results into the corresponding data processing template. Obtain the templated processing results corresponding to all the first distinguishing marker data output by the text content extraction model.

6. The financial data processing method according to claim 1 or 5, characterized in that, The preset reimbursement identification strategy includes a first identification strategy, a second identification strategy, a third identification strategy, and a fourth identification strategy. The reimbursement determination field includes a first determination field, a second determination field, a third determination field, and a fourth determination field. Before performing the step of extracting the reimbursement determination fields corresponding to all first distinguishing marker data from all templated processing results according to the preset reimbursement identification strategy, the method further includes: An automated judgment model is generated based on the first, second, third, and fourth identification strategies. The first identification strategy specifies a first judgment field, used to identify whether the corresponding first distinguishing marker data conforms to the proposed business budget range. The second identification strategy specifies a second judgment field, used to identify whether the corresponding first distinguishing marker data conforms to the proposed expense usage standard. The third identification strategy specifies a third judgment field, used to identify whether the corresponding first distinguishing marker data conforms to the legally defined business scope. The fourth identification strategy specifies a fourth judgment field, used to identify whether the corresponding first distinguishing marker data conforms to the legally defined reimbursement business type. The step of extracting the reimbursement determination fields corresponding to all first distinguishing marker data from all templated processing results according to a preset reimbursement identification strategy specifically includes: According to the first identification strategy, the first determination field of all first distinguishing marker data is extracted from all templated sorting results; According to the second identification strategy, the second determination field of all first distinguishing marker data is extracted from all templated sorting results; According to the third identification strategy, the third determination field of all first distinguishing marker data is extracted from all templated sorting results; According to the fourth identification strategy, the fourth determination field of all first distinguishing marker data is extracted from all templated sorting results.

7. The financial data processing method according to claim 6, characterized in that, The step of identifying all data in the target data to be verified that meets the reimbursement requirements and has been marked with the first distinguishing marker based on the reimbursement determination field, and then performing the second distinguishing marker, specifically includes: Input the reimbursement determination field into the automated determination model; Based on the first identification strategy and the first determination field in the reimbursement determination field, it is determined whether the target data to be verified, which currently has a first distinguishing mark added, conforms to the proposed business budget range. Based on the second identification strategy and the second determination field in the reimbursement determination field, it is determined whether the target data to be verified, which currently has a first distinguishing mark added, meets the proposed expense usage standards. Based on the third identification strategy and the third determination field in the reimbursement determination field, it is determined whether the target data to be verified, which currently has a first distinguishing mark added, conforms to the legal business scope. Based on the fourth identification strategy and the fourth determination field in the reimbursement determination field, it is determined whether the target data to be verified, which currently has the first distinguishing mark added, conforms to the legal reimbursement business type; If the target data to be verified, which has been marked with the first distinguishing tag, simultaneously meets the proposed business budget range, the proposed expense usage standards, the legal business scope, and the legal reimbursement business type, then it is marked with the second distinguishing tag; otherwise, a message indicating that reimbursement is not permitted is sent to the target data source.

8. A financial data processing device, characterized in that, include: The target data acquisition module is used to acquire target data to be verified, wherein the target data includes billing data; The first distinguishing marker adding module is used to add a first distinguishing marker to the data in the target data to be verified that meets the target adding requirements according to a preset marker adding strategy; The template-based data processing module is used to process all target data to be checked that have been marked with the first distinguishing marker according to a preset data processing template, and to obtain the template-based processing results corresponding to all data with the first distinguishing marker. The reimbursement determination field extraction module is used to extract the reimbursement determination fields corresponding to all first distinguishing marker data from all templated sorting results according to a preset reimbursement identification strategy, wherein the reimbursement identification strategy is provided by the target financial management end; The second differentiation marking module is used to identify all data in the target data to be checked that meets the reimbursement requirements based on the reimbursement determination field, and to perform the second differentiation marking. The business invoice generation module is used to generate business invoices for all target data to be verified that have been marked with a second distinction, in conjunction with a preset invoice generation template. The business ticket distribution module is used to distribute all the final generated business tickets to the corresponding receiving end according to the preset distribution strategy.

9. A computer device, characterized in that, The method includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the financial data processing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions that, when executed by a processor, implement the steps of the financial data processing method as described in any one of claims 1 to 7.

Images