A method and device for converting bill data

Abstract

The application provides a bill data universal conversion method and device, the method comprises the following steps: through a big model business flow processor and an intelligent agent, input text of a user is analyzed in a business scene and rule field extraction is performed, a recommended rule template is generated, and configuration fields of the recommended rule template are updated according to adjustment requirement text input by the user to generate a target bill conversion rule template; according to the target bill conversion rule template, source single data is universally mapped and converted to generate a bill data model of the target single, dynamic no-code automatic configuration is realized through the configuration bill conversion rule template, reusability is improved, automatic conversion of isomorphic data and heterogeneous data to a universal bill model in a complex scene can be realized, the delivery cycle is shortened, and the delivery cost is reduced; multiple cancellation relationships can be recorded according to a cancellation relationship table, an arbitrary cancellation mechanism is supported, bill redundancy is reduced, and the flexibility of cancellation relationship processing in bill conversion is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a universal document data conversion method and device. Background Art

[0002] Documents, as a primary component for collecting discrete data, are widely used in enterprise applications and carry a large number of business processes. Enterprise applications typically involve a large number of upstream and downstream business transformations, such as procurement, warehousing, settlement, and payment in enterprise financial applications, as well as business trip applications and reimbursements. All of these processes involve document-to-document references, write-offs, and transformations. Related technologies typically implement document-to-document conversions based on specific business scenarios by developing specialized business reference buttons. This rigidifies business function scenarios, requiring redevelopment and implementation of new code whenever business changes occur, resulting in long lead times and high costs. Furthermore, related technologies typically write back to the source document when recording reference and write-off relationships between documents. This requires adding additional control fields to record reference relationships, intruding on the document's business operations and resulting in high document redundancy. When the same document is referenced and written off multiple times by multiple documents, it is impossible to accurately restore the write-off process. Furthermore, when the target document is deleted or invalidated (reverse the process), arbitrary revocation is impossible, limiting flexibility. Summary of the Invention

[0003] One object of the present invention is to provide a universal document data conversion method, which realizes dynamic code-free automatic configuration by configuring document conversion rule templates, improves reusability, and can meet the needs of automatic conversion of homogeneous data and heterogeneous data to universal document models in complex scenarios, shortens delivery cycles, and reduces delivery costs; it can record multiple write-off relationships according to the write-off relationship table, supports arbitrary revocation mechanisms, reduces document redundancy, and improves the flexibility of write-off relationship processing in document conversion. Another object of the present invention is to provide a universal document data conversion device. Another object of the present invention is to provide a computer-readable medium. Another object of the present invention is to provide a computer device.

[0004] In order to achieve the above objectives, the present invention discloses a universal document data conversion method, comprising:

[0005] Through the large-model business flow processor and intelligent agent, the business scenario of the acquired user input text is analyzed and the rule fields are extracted to generate the recommendation rule template;

[0006] Through the large model business flow processor, the configuration fields of the recommendation rule template are updated according to the adjustment requirement text entered by the user;

[0007] According to the target document conversion rule template, perform general data mapping conversion on the source document data to generate the document data model of the target document.

[0008] Preferably, the user input text is a multi-round dialogue text, which includes an intention explanation dialogue text and an information collection dialogue text;

[0009] Through the large-model business flow processor and intelligent agent, the acquired user input text is analyzed for business scenarios and rule fields are extracted to generate recommendation rule templates, including:

[0010] Through the large-model business flow processor, the intent description dialogue text is recognized to generate the order type, source order information, and target order information;

[0011] Through the large-model business flow processor, the information collection dialogue text is analyzed and the corresponding business scenario is generated;

[0012] Based on the document type, source document information, and target document information, the intelligent agent extracts the source document definition, target document definition, and rule template configuration attributes through the document metadata interface and the document conversion metadata interface respectively.

[0013] The large-model business flow processor matches the business scenario, source document definition, and target document definition according to the rule template configuration attributes to generate the initial rule template.

[0014] Through the large model business flow processor, the fields of the initial rule template are supplemented according to the preset rule template knowledge base to generate a recommended rule template.

[0015] Preferably, the large model business flow processor updates the configuration fields of the recommended rule template according to the adjustment requirement text input by the user to generate a target document conversion rule template, including:

[0016] Identify the adjustment content of the adjustment request text through the large model business flow processor, including the adjustment field and the corresponding field value;

[0017] Match the adjustment fields with the configuration fields of the recommendation rule template to determine the configuration fields to be adjusted;

[0018] Update the configuration fields to be adjusted according to the field values ​​and generate the target document conversion rule template.

[0019] Preferably, the method further comprises:

[0020] A document conversion rule template identifier is set for each target document conversion rule template, and the document conversion rule template identifier is matched with a business scenario to generate a mapping relationship between the business scenario and the document conversion rule template identifier.

[0021] Preferably, the method further comprises:

[0022] In response to the automatic order generation operation triggered by the planned task, the target document conversion rule template is determined according to the document conversion rule template identifier corresponding to the business scenario of the planned task. The business scenario corresponds to the order generation type, and the order generation type is pull generation or push generation.

[0023] Preferably, the method further comprises:

[0024] Determine whether the document date and current time of the source document data are consistent with the automatic document generation settings of the planned task;

[0025] If it meets the requirements, the automatic order generation operation will be triggered;

[0026] If not, continue to determine whether the document date and current time of the source document data meet the automatic document generation settings of the planned task.

[0027] Preferably, the target document conversion rule template includes field rule settings, reference types, and parameter settings; the source document data includes homogeneous data or heterogeneous data;

[0028] According to the target document conversion rule template, perform general data mapping conversion on the source document data to generate the document data model of the target document, including:

[0029] Through the document conversion adaptation facade, heterogeneous data can be converted and standardized, or homogeneous data can be standardized and packaged to generate standardized source document data.

[0030] According to the field rule settings and reference types, perform field mapping conversion on the standardized source data to generate the target table field data;

[0031] According to the parameter settings, the target table field data is dimensionally processed to generate the document data model of the target document.

[0032] Preferably, the target document conversion rule further includes basic information, and the basic information includes a write-off relationship table;

[0033] After dimension processing is performed on the target table field data according to the parameter settings and the document data model of the target document is generated, the following steps are also included:

[0034] Generate write-off relationship records based on the data model of the write-off relationship table, the standardized source document data, and the document data model of the target document.

[0035] Preferably, the target document conversion rule also includes reverse writing settings; the basic information also includes a write-off control number;

[0036] After the write-off relationship record is generated according to the data model of the write-off relationship table and the standardized source document data and target document data model, the following is also included:

[0037] Through the set document conversion event handler, the document model of the target document is monitored for events;

[0038] If a save event is monitored, the write-off relationship record is verified based on the write-off control number;

[0039] If the verification passes, the write-off relationship record is updated to the write-off relationship table;

[0040] Through the document conversion rewrite processor that is set up, source document data is rewritten according to the rewrite settings and the write-off relationship records.

[0041] Preferably, the method further comprises:

[0042] If a deletion event is detected, the document conversion rule template corresponding to the document model of the target document is determined;

[0043] The document conversion rewrite processor is used to rewrite and roll back the source document data according to the rewrite settings and write-off relationship records in the document conversion rules.

[0044] Delete the document data of the target document to release the write-off value in the write-off relationship record.

[0045] The present invention also discloses a universal document data conversion device, comprising:

[0046] A recommendation rule template generation unit is used to parse the business scenario and extract the rule fields from the acquired user input text through a large model business flow processor and an intelligent agent to generate a recommendation rule template;

[0047] A target document conversion rule template generation unit is used to update the configuration fields of the recommended rule template according to the adjustment requirement text input by the user through the large model business flow processor to generate a target document conversion rule template;

[0048] The general data conversion unit is used to perform general data mapping conversion on the source document data according to the target document conversion rule template to generate the document data model of the target document.

[0049] The present invention also discloses a computer-readable medium on which a computer program is stored. When the program is executed by a processor, the method described above is implemented.

[0050] The present invention also discloses a computer device, including a memory and a processor, wherein the memory is used to store information including program instructions, the processor is used to control the execution of program instructions, and the processor implements the above method when executing the program.

[0051] The present invention also discloses a computer program product, comprising a computer program / instruction, which implements the above method when the computer program / instruction is executed by a processor.

[0052] The present invention uses a large-model business flow processor and an intelligent agent to perform business scenario analysis and rule field extraction on the acquired user input text to generate a recommended rule template; through the large-model business flow processor, the configuration fields of the recommended rule template are updated according to the adjustment requirement text input by the user to generate a target document conversion rule template; according to the target document conversion rule template, the source document data is converted into a general data mapping to generate a document data model of the target document, and dynamic code-free automatic configuration is achieved by configuring the document conversion rule template to improve reusability, which can meet the automatic conversion of homogeneous data and heterogeneous data to a general document model in complex scenarios, shorten the delivery cycle, and reduce delivery costs; it can record multiple write-off relationships according to the write-off relationship table, support an arbitrary revocation mechanism, reduce document redundancy, and improve the flexibility of write-off relationship processing in document conversion. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 A schematic diagram of the structure of a universal document data conversion system provided by an embodiment of the present invention;

[0055] Figure 2 A schematic diagram of the structure of a document conversion rule template provided by an embodiment of the present invention;

[0056] Figure 3 A flowchart of a general document data conversion method provided by an embodiment of the present invention;

[0057] Figure 4 A flowchart of another universal document data conversion method provided by an embodiment of the present invention;

[0058] Figure 5 A schematic structural diagram of a general document data conversion device provided by an embodiment of the present invention;

[0059] Figure 6 A schematic structural diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0061] To facilitate understanding of the technical solution provided by this application, the relevant contents of the technical solution of this application are first explained below. A document is an abstract data model, business model, and business component used to process discrete business data collection, review, and other forms. The document data model generally has a main table and one or more sub-tables, which correspond to the main information and detailed (row) information of the document respectively. Common documents include: leave applications, loan applications, business trip applications, expense reimbursement applications, etc. The present invention develops a universal document conversion system that can efficiently realize the automatic conversion between source document and target document data. Specifically, it can realize the mapping and conversion of source document data of homogeneous data (documents) and heterogeneous data (non-documents) to the document data model of the target document through the configured document conversion rule templates under different business scenarios; the universal document conversion system can meet scenarios such as pull generation and push generation, including but not limited to automatic data matching and conversion at a fixed time; it can support the reference / generation relationship between the main table and the sub-table, including but not limited to: "master-leading-master", "sub-leading-master" and "sub-leading-sub", and needs to support merging and conversion according to the set dimension combination; after the conversion is completed, it can automatically record the cancellation relationship, perform cancellation control, and provide a reverse writing mechanism for the source document data; the document conversion rule template can be dynamically configured without code to form a conversion rule template for reuse, support both the design period and the operation period, and facilitate business personnel to perform customized configuration; the universal conversion of document data needs to cooperate with document design and operation, and provide corresponding packaged plug-ins, actions and interfaces, etc., to achieve out-of-the-box use.

[0062] Figure 1 A schematic diagram of the structure of a document data universal conversion system provided by an embodiment of the present invention is shown as follows: Figure 1 As shown, the system adopts a layered architecture design, including a runtime layer and a design layer for front-end applications, and a model layer and an adaptation layer for back-end rule processing.

[0063] The runtime layer primarily provides user interaction portals, which consist of a series of interface buttons, screens, and scheduled tasks. These portals include, but are not limited to, pull-based document generation actions, pull-based entry controls, pull-based document generation plug-ins, pull-based reference interfaces, push-based document generation actions, and push-based scheduled tasks. Users can trigger universal document data conversion by clicking on these interface portals.

[0064] The design phase mainly provides business personnel with document conversion rule template configuration and publishing capabilities, and customized configuration of pull-type or push-type rule templates based on different business scenarios for users' front-end document business processing. Figure 2 A schematic diagram of the structure of a document conversion rule template provided by an embodiment of the present invention, such as Figure 2 As shown, the document conversion rule template includes but is not limited to basic information, field rule settings, back-write settings, parameter settings, and automatic document generation settings. Basic information includes document generation type, reference type, source document information, target document information, write-off control number, and write-off relationship table. Document generation type includes pull generation or push generation, and reference type includes master-master, sub-master, or sub-sub. Field rule settings include query conditions and field mapping. Query conditions are to fill in the fields to be queried. Field mapping includes the mapping relationship between the source document master table and the target document master table, the mapping relationship between the source document sub-table and the target document sub-table, and the mapping relationship between the source document master table and the target sub-table. Back-write settings include back-write field mapping and back-write timing. Parameter settings include reference interface parameters, document generation execution parameters, and document generation saving parameters. Document generation execution parameters include summary dimensions, summary indicators, or document generation dimensions. Document generation saving parameters include merging documents or generating documents one by one. Automatic order generation settings include order generation timing, order generation conditions, and order generation dimensions. Order generation timing is the configurable time to trigger order generation, for example, the difference between the system date and the document date is 1. Order generation conditions are the configurable conditions to trigger order generation, for example, when the source document is saved or when process approval is completed. Order generation dimensions are referenced table fields.

[0065] The model layer includes the document conversion rule processing model, the universal master table data model, the universal sub-table data model, the dimension mapping data model, the write-off relationship table data model, the document conversion adaptation facade, the document conversion write-back processor, and the document conversion event processor. The document conversion rule processing model parses the document conversion rule template defined during the design phase and provides it to the adaptation layer for use. The adaptation facade processes the source document data received based on the document conversion rule template and converts it into the universal master table data model and universal sub-table data model. Based on the converted document data model, combined with the document conversion rule template, the dimension mapping data model, and the write-off relationship data model, it performs dimension aggregation and write-off relationship updates. The document conversion adaptation facade is used to provide the adapter interface specification encapsulation of various source document data types to the lower-level adaptation layer, and to register and collect the implemented adapters; the document conversion rewrite processor provides a rewrite processing mechanism for source document data, which is used to rewrite the write-off relationship records of the write-off relationship table to the source document data; the document conversion event processor is used to monitor the save or delete events of the target document model, and process the target document data model and the corresponding write-off relationship table and source document data based on different monitoring events.

[0066] The adaptation layer primarily consists of data adapters registered by the source document data provider. Built-in adapters include, but are not limited to, document data adapters, report data adapters, query data adapters, and other data adapters. Source data (homogeneous or heterogeneous) is adapted according to the document conversion rule template and sent to the document conversion adaptation facade in the model layer. The document conversion rule model then converts the data received by the document conversion adaptation facade into a common master table data model and common sub-table data models.

[0067] In the technical solution provided by the embodiment of the present invention, the business scenario analysis and rule field extraction of the acquired user input text are performed through the large model business flow processor and the intelligent agent to generate a recommended rule template; the recommended rule template is updated according to the configuration field input by the user through the intelligent agent to generate a target document conversion rule template; according to the target document conversion rule template, the source document data is converted into a general data mapping to generate a document data model of the target document, and dynamic code-free automatic configuration is achieved by configuring the document conversion rule template to improve reusability, which can meet the automatic conversion of homogeneous data and heterogeneous data to a general document model in complex scenarios, shorten the delivery cycle, and reduce delivery costs; it can record multiple write-off relationships according to the write-off relationship table, support arbitrary revocation mechanism, reduce document redundancy, and improve the flexibility of write-off relationship processing in document conversion.

[0068] It is worth mentioning that Figure 1 The document data universal conversion system shown is also applicable to Figure 3 or Figure 4 The general conversion method of document data will not be described here.

[0069] The following uses the document data universal conversion device as an example to illustrate the implementation process of the document data universal conversion method provided by the embodiment of the present invention. It is understood that the execution subject of the document data universal conversion method provided by the embodiment of the present invention includes but is not limited to the document data universal conversion device.

[0070] Figure 3 A flowchart of a general method for converting document data provided by an embodiment of the present invention is shown in FIG. Figure 3 As shown, the method includes:

[0071] Step 101: Use the large model business flow processor and agent to perform business scenario analysis and rule field extraction on the acquired user input text to generate a recommendation rule template.

[0072] In the embodiment of the present invention, the user input text is a multi-round dialogue text, and the multi-round dialogue text includes intention explanation dialogue text and information collection dialogue text.

[0073] In an embodiment of the present invention, the large model business flow processor is a pre-trained model for orchestrating business flows, and has natural language processing (NLP) capabilities. For multi-round conversation texts, it can inject pre-trained language models such as BERT and Transformer to understand user input and perform intent recognition, scenario analysis and other functions; it also has the function of a rule engine to realize business process automation, allowing clear business rules to be defined, automatic field matching and filling, so as to automatically generate target document conversion rule templates, reduce labor costs and improve the degree of automation; it also has metadata synchronization and management functions, involving database query optimization, indexing technology and distributed storage solutions to ensure data consistency and efficient access.

[0074] In an embodiment of the present invention, the Agent intelligent body is the execution unit in the entire system, responsible for completing specific tasks according to the guidance of the large-scale business flow orchestration, including but not limited to: interacting with the document conversion rule template service to synchronize necessary metadata information; extracting corresponding data information from the source document information and the target document information; calling the encapsulated document conversion metadata interface (API) and the document metadata API, generating specific rule definitions based on the rule template recommendation generated by the large-scale business flow orchestration; completing the creation, verification, saving and publishing of the target document conversion rule template by calling various APIs provided by the document conversion rule template service (such as the new / temporary storage API, the verification / save API, the publish API, etc.).

[0075] It is worth noting that each API is encapsulated according to the Model Context Protocol (MCP) and provided to the Agent or large model business flow processor for calling.

[0076] Step 102: Through the large model business flow processor, the configuration fields of the recommended rule template are updated according to the adjustment requirement text input by the user to generate a target document conversion rule template.

[0077] In an embodiment of the present invention, a user can be asked to identify areas requiring adjustment, allowing the user to enter a textual adjustment request. The textual adjustment request is the content of the recommendation rule template that the user needs to modify, add, delete, or update based on actual needs. Configuration fields are the fields to be adjusted that are parsed from the textual adjustment request.

[0078] As another optional solution, analyze the document conversion business scenario to be implemented. First, determine the document generation type and reference type to be used. Then, configure and debug each one according to the general template to complete the configuration of the corresponding conversion rules and publish the target document conversion rule template.

[0079] In this embodiment of the present invention, the target document conversion rule template includes, but is not limited to, basic information, field rule settings, reverse writing settings, parameter settings, and automatic document generation settings. Basic information includes the generation document type, reference type, source document information, target document information, write-off control number, and write-off relationship table.

[0080] Order generation types include pull generation and push generation. Pull generation is a method of generating data from a source document to a target document by referencing a source document. Push generation is a method of generating data from a source document to a target document by actively generating a target document.

[0081] Reference types include master-master, sub-master, or sub-master. A master-master is a target document master table that references a source document master table, generally referencing the source document number to establish business write-off relationships and joint queries. A sub-master is a target document sub-table that references multiple source document master tables to generate target document sub-table row information (which can be combined and summarized by dimension), establish business write-off relationships and joint queries. A sub-master is a target document sub-table that references at least one source document sub-table row information to generate target document sub-table row information (which can be combined and summarized by dimension), establish business write-off relationships and joint queries, and supports referencing multiple sub-tables of a source document to the target document at once.

[0082] Furthermore, the reference type can also include sub-master push, that is, the push-based generation method of sub-references, in which the row information of the source single sub-table is pushed to generate (can be combined and summarized by dimension) the row information of multiple target single master tables.

[0083] Furthermore, document conversion also supports a combination of mapping methods. Specifically, in pull-based generation, the mapping method for sub-primers also includes the target single master table and sub-tables referencing multiple source single master tables; the mapping method for sub-primers also includes the target single master table and sub-tables referencing multiple source single master tables, or the target single master table and sub-tables referencing multiple source single sub-tables. Specifically, in push-based generation, the mapping method for sub-primers also includes the target single master table and sub-tables referencing multiple source single master tables; the mapping method for sub-primers also includes the target single master table and sub-tables referencing multiple source single master tables, or the target single master table and sub-tables referencing multiple source single sub-tables.

[0084] Source document information is the basic information about the source document data, including but not limited to the source document number, source document definition, source document sub-table ID, and source document master table ID. A source document is the original document or data record that initiates a business process and is typically the starting point or basis for business processing. For example, when reimbursement is required, an application must be submitted before reimbursement. In the relationship between a reimbursement document and an application, the application is the source document.

[0085] Target document information includes basic information about the target document data, including but not limited to the target document number, target document definition, target document master table ID, and target document sub-table ID. A target document is a new document generated from a source document (document or data record) during a business process and is typically the target of subsequent business processing. For example, if a reimbursement requires an application before a reimbursement is made, in the relationship between a reimbursement document and an application document, the reimbursement document is the target document.

[0086] It is worth noting that, since the target order is generated later, the target order number can be generated when saving, and the target order number can be empty in the target order information before the target order is generated.

[0087] The write-off control number sets the upper limit for a source document to be referenced (or generated) by a target document. This controls the total amount of source documents that can be repeatedly referenced (or generated). Optionally, the control number can be the amount or quantity of the source document.

[0088] The write-off relationship table is a collection of write-off records used to record the correspondence between target documents and source documents, including but not limited to the row representation, target document number, target document definition, target document master table ID, target document sub-table ID, source document number, source document definition, source document sub-table ID, current write-off value (amount / quantity), and document conversion rule template ID.

[0089] It is worth noting that the source document must have a source document number, so there is no need to redundantly store the source document master table ID to save space; since the target document number may be generated when it is saved (only the target document ID is created when it is newly created), it is necessary to record the target document ID first and then update the target document number when the target document is saved.

[0090] Step 103: Perform general data mapping transformation on the source document data according to the target document transformation rule template to generate a document data model for the target document.

[0091] In an embodiment of the present invention, the target document conversion rule template further includes field rule settings and parameter settings; the source document data may include homogeneous data or heterogeneous data. Specifically, according to the field rule settings and parameter settings, a universal data mapping conversion is performed on the homogeneous or heterogeneous data to generate a document data model for the target document.

[0092] In the technical solution provided by the embodiment of the present invention, the business scenario analysis and rule field extraction of the acquired user input text are performed through the large model business flow processor and the intelligent agent to generate a recommended rule template; the recommended rule template is updated according to the configuration field input by the user through the intelligent agent to generate a target document conversion rule template; according to the target document conversion rule template, the source document data is converted into a general data mapping to generate a document data model of the target document, and dynamic code-free automatic configuration is achieved by configuring the document conversion rule template to improve reusability, which can meet the automatic conversion of homogeneous data and heterogeneous data to a general document model in complex scenarios, shorten the delivery cycle, and reduce delivery costs; it can record multiple write-off relationships according to the write-off relationship table, support arbitrary revocation mechanism, reduce document redundancy, and improve the flexibility of write-off relationship processing in document conversion.

[0093] Figure 4 A flowchart of another general document data conversion method provided by an embodiment of the present invention is as follows: Figure 4 As shown, the method includes:

[0094] Step 201: Use the large model business flow processor and intelligent agent to perform business scenario analysis and rule field extraction on the acquired user input text to generate a recommendation rule template.

[0095] In the embodiment of the present invention, step 201 specifically includes:

[0096] Step 2011: Use the large model business flow processor to perform intent recognition on the intent description dialogue text and generate the order type, source order information and target order information.

[0097] In an embodiment of the present invention, the intent description dialogue text is the text input by the user. The large model business flow processor uses a pre-trained NLP model to perform intent recognition on the intent description dialogue text and generate the order type, source order information and target order information.

[0098] It is worth noting that by asking the user questions about the document to be processed and the type of document, the intention description dialogue text related to the source document information and the target document information can be elicited.

[0099] Step 2012: Use the large model business flow processor to perform scenario analysis on the information collection dialogue text and generate corresponding business scenarios.

[0100] In an embodiment of the present invention, the large-model business flow processor performs scenario analysis on the information collection dialogue text through a pre-trained NLP model and outputs the corresponding business scenario.

[0101] It is worth mentioning that by asking users about the specific application scenarios of document conversion, information collection dialogue text related to the business scenario can be elicited.

[0102] Step 2013: The Agent extracts the source document definition, target document definition, and rule template configuration properties based on the document type, source document information, and target document information, respectively, through the document metadata API and document conversion metadata API. The source document definition refers to the data structure, fields, attributes, and related business rules of the source document information; the target document definition refers to the data structure, fields, attributes, and related business rules of the target document information to be generated. The rule template configuration properties are the set of rules used to control how the source document is converted to the target document. The rule template configuration properties serve as the bridge between the source and target documents.

[0103] In an embodiment of the present invention, the agent obtains rule template configuration attributes by calling the document conversion metadata API, and the rule template configuration attributes can be rule template configuration attributes corresponding to the document type; the agent extracts the corresponding source document definition and target document definition according to the source document information and the target document information by calling the document metadata API.

[0104] Step 2014: Use the large model business flow processor to match the business scenario, source order definition, and target order definition according to the rule template configuration attributes to generate an initial rule template.

[0105] Specifically, the large model business flow processor matches the source document definition and the target document definition with the basic information in the rule template configuration attributes, establishes the field mapping rules between the source document and the target document, and establishes the basic information under the document conversion rule template to generate the initial rule template.

[0106] Step 2015: Through the large model business flow processor, according to the preset rule template knowledge base, the fields of the initial rule template are supplemented to generate a recommended rule template.

[0107] In an embodiment of the present invention, the rule template knowledge base stores a variety of document conversion rule templates and basic information, field mapping rule settings, back-writing settings, parameter settings and automatic document generation settings under each document conversion rule template.

[0108] Specifically, the large model business flow processor matches the basic information of the initial rule template with the basic information of the document conversion rule template stored in the rule template knowledge base, fills the corresponding field mapping rule settings, back-write settings, parameter settings and automatic order generation settings into the initial rule template, and generates a recommended rule template.

[0109] Furthermore, the recommendation rule template is visually displayed to the user, and the user is asked whether the recommendation rule template needs to be modified, thereby leading to the configuration fields that need to be modified.

[0110] Step 202: Through the large model business flow processor, the configuration fields of the recommended rule template are updated according to the adjustment requirement text input by the user to generate a target document conversion rule template.

[0111] In an embodiment of the present invention, the large model business flow processor identifies the adjustment content of the adjustment requirement text through the NLP model, and the adjustment content includes the adjustment field and the corresponding field value; matches the adjustment field with the configuration field of the recommendation rule template to determine the configuration field to be adjusted; updates the configuration field to be adjusted according to the field value to generate an updated recommendation rule template; visually displays the updated recommendation rule template to the user, and asks the user whether the recommendation rule template needs to be modified. If the user enters the adjustment requirement text that needs to be modified, repeat the step of identifying the adjustment content of the adjustment requirement text; if the user does not enter the adjustment requirement text, the updated recommendation rule template is determined as the target document conversion rule template.

[0112] Furthermore, by asking the user whether to confirm the release of the target document conversion rule template, a new / temporary storage option, a verification / save option and a release option can be provided; in response to the new / temporary storage option, the agent calls the rule template new / temporary storage API to create / temporarily store the target document conversion rule template; in response to the verification / save option, the agent calls the rule template verification / save API to verify / save the target document conversion rule template; in response to the release option, the agent calls the rule template release API to release the target document conversion rule template.

[0113] Step 203: Set a document conversion rule template identifier for each target document conversion rule template, and match the document conversion rule template identifier with the business scenario to generate a mapping relationship between the business scenario and the document conversion rule template identifier.

[0114] In the embodiment of the present invention, the document conversion template identifier is used to uniquely identify the corresponding document conversion rule template and establish a corresponding relationship between the business scenario, the document conversion rule template identifier and the target document conversion rule template.

[0115] It is worth noting that the document conversion rule template corresponding to the business scenario can be pre-configured and assigned to the document conversion rule template identifier corresponding to the business scenario.

[0116] It's worth noting that in subsequent practical applications, if a user needs to create a new target document conversion rule template, they can follow the process from steps 201 to 203. If a user needs to call a target document conversion rule template from a historical business scenario, they can directly call the target document conversion rule template corresponding to the historical business scenario or document conversion rule template identifier. Furthermore, users can adapt the called target document conversion rule template to their actual needs. This calling method can increase the reuse rate of document conversion rule templates, reduce costs, and improve automation and document conversion efficiency.

[0117] This invention, through the collaborative work of a large-scale business flow processor and an agent, enables automated parsing of user-entered text and generation of rule templates, significantly improving the efficiency and intelligence of document conversion configuration. Through configurable field mapping, a write-back mechanism, and multi-timing triggering capabilities, the system's adaptability to complex business scenarios is enhanced, improving the flexibility and data consistency of document write-off processing. Furthermore, it supports the rapid reuse and adjustment of historical rule templates, effectively reducing redundant configuration costs and improving overall business processing efficiency and automation capabilities.

[0118] Step 204: Determine whether the document date and current time of the source document data comply with the automatic document generation settings of the planned task. If so, execute step 205; if not, repeat step 204.

[0119] In the embodiment of the present invention, each step is performed by a document data universal conversion device.

[0120] In the embodiment of the present invention, the source document data includes homogeneous data or heterogeneous data. The document date is the date marked on the source document data.

[0121] For example, consider the automatic order generation setting for a scheduled task, where the document date is the day before the current time. If the source document date is the day before the current time, this indicates that the source document date and current time meet the automatic order generation setting for the scheduled task, triggering the automatic order generation operation for the scheduled task and continuing with step 205. If the source document date is not the day before the current time, this indicates that the source document date and current time do not meet the automatic order generation setting for the scheduled task, and the automatic order generation operation for the scheduled task will not be triggered. The process continues with step 204 until the automatic order generation setting is met.

[0122] It is worth noting that the automatic order generation setting can be set according to actual needs, and the embodiment of the present invention does not limit this. The automatic order generation setting is configured in the planned task and is bound to the target document conversion rule template identifier corresponding to the corresponding current business scenario.

[0123] As an alternative, business personnel can manually trigger document generation for a specific business scenario. Pull generation involves configuring a pull-based document generation action or input control on the target document and binding it to the target document conversion rule template identifier corresponding to the current business scenario. Push generation involves configuring a push-based document generation action on the source document or source document list and binding it to the target document conversion rule template identifier corresponding to the current business scenario.

[0124] Step 205: In response to the automatic document generation operation triggered by the planned task, a target document conversion rule template is determined according to the document conversion rule template identifier corresponding to the business scenario of the planned task.

[0125] In this embodiment of the present invention, business scenarios correspond to order generation types, which can be pull-based or push-based. Pull generation and push generation differ in whether the operation is initiated from the source document or the target document. Pull generation is initiated from the target document, while push generation is initiated from the source document.

[0126] In the embodiment of the present invention, a corresponding target document conversion rule template is determined according to the document conversion rule template identifier, and the target document conversion rule template is a template corresponding to the business scenario.

[0127] It is worth noting that business personnel can select and configure document conversion rule templates based on different complex scenarios. Without code development, they can configure document conversion rule templates that meet various business scenarios, improve template delivery efficiency, and thus improve document conversion processing efficiency, greatly enhancing the response efficiency of business consultants to business scenario requirements.

[0128] Step 206: Through the document conversion adaptation facade that is set, the heterogeneous data is format converted and standardized encapsulated, or the homogeneous data is standardized encapsulated to generate standardized source document data.

[0129] In this embodiment of the present invention, the document adaptation facade adopts the Facade design pattern. This pattern primarily simplifies the access interfaces between the document conversion rule processing model and various data adapters. These data adapters implement a unified Facade interface, ensuring model layer stability. The Facade design pattern provides a simplified, unified interface for a complex system or set of complex interfaces, hiding the system's complexity and making it easier for users to interact with the system.

[0130] Specifically, the document conversion adaptation facade parses the data format of heterogeneous data, converts the data format of heterogeneous data into a data format that conforms to the document conversion rule template, and encapsulates the heterogeneous data according to the preset encapsulation specifications to generate standardized source document data; or, encapsulates the homogeneous data according to the preset encapsulation specifications to generate standardized source document data.

[0131] By introducing the facade design pattern, the present invention makes the model layer rely only on the facade interface, without having to worry about the implementation details of the underlying specific adapter, thereby reducing the degree of coupling; new adapters only need to implement the standard interface, without affecting the existing business logic, thereby improving maintainability and scalability; the adaptation process is uniformly controlled by the model layer to avoid frequent modifications due to underlying changes, thereby enhancing system stability; a consistent calling entry is provided to reduce duplicate code, standardize the interaction process between systems, and improve development efficiency.

[0132] Step 207: Perform field mapping conversion on the standardized source data according to the field rule settings and reference types to generate target table field data.

[0133] In an embodiment of the present invention, the field rule setting includes query conditions and field mapping. The query conditions are to fill in the fields to be queried. The field mapping includes the mapping relationship between the source order main table and the target order main table, the mapping relationship between the source order sub-table and the target order sub-table, and the mapping relationship between the source order main table and the target sub-table.

[0134] Specifically, if the reference type is master-reference-master, according to the mapping relationship between the source document master table and the target document master table, the fields of the source document master table in the standardized source document data are converted into field mappings to generate the target master table field data.

[0135] If the reference type is sub-reference, according to the mapping relationship between the source order sub-table and the target order sub-table, the fields of the source order sub-table in the standardized source order data are converted into field mappings to generate the target sub-table field data.

[0136] If the reference type is sub-reference-master, according to the mapping relationship between the source document master table and the target sub-table, the fields of the source document master table in the standardized source document data are mapped and converted to generate the target sub-table field data.

[0137] Generate target table field data based on target main table field data and target sub-table field data.

[0138] Step 208: Perform dimension processing on the target table field data according to the parameter settings to generate the document data model of the target document.

[0139] In an embodiment of the present invention, parameter settings include reference interface parameters, order generation execution parameters, and order generation saving parameters. Reference interface parameters include, but are not limited to, allowing multiple selections, allowing cross-document definition selections, referencing the interface to jointly query source documents, and displaying unwritten-off amounts. Order generation execution parameters include, but are not limited to, summary dimensions, summary indicators, or order generation dimensions. Order generation saving parameters include, but are not limited to, merging orders or generating orders one by one.

[0140] Specifically, according to the reference interface parameters, order generation parameters, and order save parameters, the target table field data is dimensionally split, combined, and summarized to generate the target document's document data model. For example, the reference interface parameters include: Allow Multiple Selection: Whether multiple selections are allowed in the reference interface list data; Allow Cross-Document Definition Selection: Whether source document data from different document types can be selected simultaneously; Reference Interface Linked Query: Whether the reference interface list data can be linked to source document details by penetrating the document number column; Display Unreconciled Amount: Whether the remaining unreconciled amount of the source document is displayed. If the order generation parameter is a summary dimension, and the summary dimension is the department dimension, only one summary row is generated for the same department, the target table field data is processed according to the department dimension to generate the target document's document data model.

[0141] In an embodiment of the present invention, merged order generation or item-by-item order generation is available in push generation mode. Merged order generation pushes multiple source orders to generate one target order. Item-by-item order generation responds to order generation dimensions and summary indicators, generating multiple target orders according to the configured dimensions.

[0142] Step 209: Generate a write-off relationship record according to the data model of the write-off relationship table, the standardized source document data, and the document data model of the target document.

[0143] In the embodiment of the present invention, the data model of the write-off relationship table is shown in Table 1:

[0144] Table 1

[0145]

[0146] In this embodiment of the present invention, the write-off relationship table is used to store the conversion relationship between the target document and the source document, as well as the current write-off value for that conversion. Specifically, a new write-off relationship record is generated based on the source document number, source document definition, and source document sub-table ID in the standardized source document data; the target document number, target document definition, target document master table ID, target document sub-table ID in the target document's document data model; the current write-off value; and the document conversion rule template identifier.

[0147] It is worth noting that the source document must have a source document number, so there is no need to redundantly store the source document master table ID. Since the target document number may be generated when it is saved (only the target document master table ID and target document sub-table ID are available when the document is newly created), it is necessary to first record the target document master table ID and target document sub-table ID, and then update the target document number when the target document is saved.

[0148] Step 210: Monitor the document model of the target document through the document conversion event handler. If a save event is detected, execute step 211; if a delete event is detected, execute step 214.

[0149] In this embodiment of the present invention, a document model includes, but is not limited to, a document data model, corresponding model transformation rules, and model actions. A document transformation event handler monitors all events on the document model. Model transformation rules are the rules in the document transformation rule template corresponding to the document data model, and model actions are the actions executed by the document data model.

[0150] In an embodiment of the present invention, the document conversion event processor continuously monitors the document model of the target document, and the monitored events include save events and delete (cancel) events; if a save event is monitored, it indicates that the document data model of the target document needs to be saved, and step 211 is continued to be executed; if a delete (cancel) event is monitored, it indicates that the document data model of the target document needs to be deleted, and step 214 is continued to be executed.

[0151] Step 211: Verify the write-off relationship record based on the write-off control number. If the verification passes, proceed to step 212; if the verification fails, the process ends.

[0152] In this embodiment of the present invention, the write-off control number is the upper limit of the number of target documents that can reference (or generate) a source document. This controls the total amount of source documents that can be repeatedly referenced (or generated). Alternatively, the write-off control number can be the amount or quantity of the source document.

[0153] Specifically, if the current write-off value in the write-off relationship record is less than or equal to the write-off control number, it indicates that the reference / generation upper limit has not been exceeded, the verification passes, and step 212 is continued; if the current write-off value in the write-off relationship record is greater than the write-off control number, it indicates that the reference / generation upper limit has been exceeded, the verification fails, and the process ends.

[0154] Step 212: Update the write-off relationship record to the write-off relationship table.

[0155] In an embodiment of the present invention, if the document number of the target document is generated when it is saved, the target document number of the write-off relationship record is updated at the same time; the updated write-off relationship record is added to the write-off relationship table to update the write-off relationship table.

[0156] Step 213: Use the document conversion reverse write processor to reverse write the source document data according to the reverse write settings and the write-off relationship records. The process ends.

[0157] In this embodiment of the present invention, write-back settings include write-back field mapping and write-back timing. Write-back field mapping configures the mapping between the fields and values ​​of the source document to be written back. Typically, the values ​​are mapped to fields of the target document. When writing back, the target document fields are written back to the source document fields. For example, the reimbursement amount on an asset report (target document) is written back to the accumulated written-off amount field on a loan document (source document).

[0158] It is worth noting that the reverse writing timing can be set according to actual needs. The default reverse writing timing is when the target order save event is detected, and when the target order delete (cancel) event is detected.

[0159] For example, the source document data also includes a cancellation status. This field is a Boolean type and indicates whether the source document has been cancelled. If a save event occurs on the target document model, the cancellation status of the source document data is updated to "Cancelled" after the cancellation relationship table is updated.

[0160] It is worth noting that other business fields that need to be backwritten and updated can also be configured in the source data. The specific business fields can be set according to actual needs and are not limited in this embodiment of the present invention. The backwriting update method includes overwriting or accumulation (subtraction).

[0161] Step 214: Determine the document conversion rule template corresponding to the document data model of the target document.

[0162] In an embodiment of the present invention, based on the cancellation relationship table, the corresponding document conversion rule template identifier is determined according to the target document number of the document data model of the target document; according to the document conversion rule template identifier, the corresponding document conversion rule template is determined, and according to the document data model of the target document, the determined document conversion rule template is traversed to determine the fields that need to be rewritten.

[0163] Step 215: Through the set document conversion rewrite processor, the source document data is rewritten and rolled back according to the rewrite settings and cancellation relationship records in the determined document conversion rules.

[0164] In this embodiment of the present invention, write-back settings include write-back field mapping and write-back timing. Write-back field mapping configures the mapping between the fields and values ​​of the source document to be written back. Typically, the values ​​are mapped to fields of the target document. When writing back, the target document fields are written back to the source document fields. For example, the reimbursement amount on an asset report (target document) is written back to the accumulated written-off amount field on a loan document (source document).

[0165] It is worth noting that the reverse writing timing can be set according to actual needs. The default reverse writing timing is when the target order save event is detected, and when the target order delete (cancel) event is detected.

[0166] For example, the source document data also includes a cancellation status. This field is a Boolean type and indicates whether the source document has been cancelled. If the target document model is deleted or invalidated, the cancellation status of the source document data is rewritten back to uncancelled after the cancellation relationship table is updated.

[0167] It is worth noting that other business fields that need to be written back and rolled back can also be configured in the source data. The specific business fields can be set according to actual needs and are not limited in this embodiment of the present invention. The writing back and rolling back methods include overwriting or accumulation (subtraction).

[0168] Step 216: Delete the document data of the target document and release the write-off value in the write-off relationship record.

[0169] In the embodiment of the present invention, after the source document data is written back and rolled back, the document data of the target document is deleted, and the write-off value in the write-off relationship record is released.

[0170] By implementing a document conversion rewrite processor and a flexible rewrite mechanism, this invention can record multiple write-off relationships based on the write-off relationship table and support arbitrary revocation operations, effectively avoiding document data redundancy and improving the flexibility and accuracy of write-off processing. Furthermore, through configurable field mapping and a multi-timing trigger mechanism, the system's adaptability to complex business scenarios is enhanced, significantly optimizing data consistency and business controllability during the document conversion process.

[0171] The following describes the general document data conversion process using a specific push-based generation example. Document conversion rules are a highly versatile tool for establishing data reference relationships, in addition to fixed product-specific business data reference scenarios. They support both system-initiated triggering (push-based generation scenarios) and user-generated document references (pull-based generation scenarios). While ensuring flexibility, they also ensure data accuracy through the management of settlement relationships.

[0172] For example, generating a receipt from a bank statement for Project XX. After the bank interface receives the receipt's bank statement, the system automatically generates a receipt based on multiple bank statements from the same organization. The bank statement information is displayed in the receipt subtable and the accounts receivable are reconciled. After the receipt is automatically submitted and confirmed, a receipt voucher is generated, ensuring the timeliness and accuracy of financial data. Furthermore, through reconciliation relationship management, duplicate receipts are avoided, facilitating subsequent reconciliation and auditing.

[0173] Related accounting treatment:

[0174] Debit: Bank deposit.

[0175] Credit: Accounts Receivable Customer A.

[0176] Credit: Accounts Receivable Customer B.

[0177] Order type: push generation.

[0178] Reference relationship: The sub-table references the main table (sub-table references main table), that is, the collection data of the receipt comes from the bank statement main table.

[0179] Write-off relationship: Stores the write-off relationship to ensure that the correspondence between bank statements and receipt forms is traceable.

[0180] Generate order timing: Batch select multiple records in the bank statement list and manually trigger it through the push-to-generate button.

[0181] Conditions for generating bank statements: The bank statement date is the day before the system time.

[0182] The configuration steps are as follows:

[0183] The first step is to create a bank statement list and a write-off relationship table. The key fields and field storage logic contained in the write-off relationship table are shown in Table 2:

[0184] Table 2

[0185]

[0186] Step 2: Configure document conversion rules:

[0187] Order type: Select "Push generation".

[0188] Reference type: Select "Master fader sub-table references master table" (sub-fader references master).

[0189] Write-off relationship: Bind the write-off relationship table and enable "Store Write-off Relationship".

[0190] Step 3: Field matching:

[0191] Configure sub-table field mapping, that is, map the bank statement main table information to the payment receipt sub-table transaction information.

[0192] Step 4: Reverse settings:

[0193] The reverse writing setting is optional. To update the reference status of a bank statement, configure the reverse writing field. After a receipt is generated from a bank statement, the reference status of the bank statement is set to "referenced". In the bank statement list, you can use the reference status to query referenced bank statements.

[0194] Step 5: Automatic order generation:

[0195] Generation timing: Scheduled tasks trigger automatic order generation through regular, automated execution. Configure the automatic order generation schedule to periodically check for unprocessed bank statements that meet the conditions configured for automatic order generation and push-generate receipts.

[0196] Generation condition: Document date in the master table = system date - 1. When the scheduled task is executed, bank statements with a document date of one day before the current system time will automatically generate receipts. Bank statements that do not meet this condition will not generate receipts.

[0197] Document Generation Dimension: Set to the Organization field of the main table. When the scheduled task is executed, bank statements with the same organization are generated into the subtable of the same receipt. Bank statements with different organizations are generated into different receipts.

[0198] The processing logic during the actual conversion process:

[0199] The first step is that the system executes regularly through the configured scheduled task execution cycle.

[0200] Step 2: During execution, filter the bank statement list according to the generation conditions in the automatic document generation configuration, that is, the document date = system date - 1 and no collection document has been generated (there is no record of the write-off relationship).

[0201] The third step is to group the filtered data according to the order generation dimension (main table organization) configured for automatic order generation, that is, the data with the same organization in the bank flow list will be generated on one receipt.

[0202] Step 4: Import the bank statement fields into the main and sub-tables of the single receipt document according to the configured field matching rules. For example, import the organization structure from the bank statement main table into the organization structure from the receipt main table, and import the bank account number from the bank statement into the bank account number field of the receipt sub-table.

[0203] Step 5. After the data is brought in, the system automatically saves the receipt, stores the write-off relationship table, writes back the bank statement, and updates the source document status field to "referenced".

[0204] Note: The system automatically stores the write-off relationship: the receipt ID is automatically generated, the receipt number is written into the target document number, the bank statement number is written into the target document number, and the bank statement amount is written into the amount field of the write-off relationship table.

[0205] Step 6: Complete the receipt process and generate a voucher for approval.

[0206] The following describes the general conversion process of document data using a specific pull-based generation example, taking the asset report of project XX quoting loan document data as an example.

[0207] Business scenario description:

[0208] Asset module reimbursements require reference to personal loan documents and write-offs of personal loans. Linking asset reimbursements with personal loans ensures clear fund usage, helps companies control loan usage, and ensures timely write-offs of personal loans.

[0209] Related accounting treatment:

[0210] When a personal loan occurs:

[0211] Debit: Reserve Fund - Personal Loan.

[0212] Credit: Bank deposit.

[0213] When reporting assets:

[0214] Debit: Fixed assets.

[0215] Credit: Bank deposit.

[0216] Credit: Reserve Fund - Personal Loan.

[0217] Business logic:

[0218] Order generation type: Pull generation (manually triggered by the user).

[0219] Reference relationship: The sub-table references the main table. That is, the sub-table data of the asset statement comes from the main table data of the loan statement.

[0220] Write-off relationship: Store write-off relationships to ensure that the correspondence between loan documents and asset reports is traceable.

[0221] Parameter settings:

[0222] Multiple selection of loan orders is allowed.

[0223] Supports cross-document definition selection.

[0224] The reference interface displays the unwritten-off amount column to facilitate user verification.

[0225] Supports joint query of source documents to improve operational convenience.

[0226] Configuration steps:

[0227] The first step is to create a list of loan documents.

[0228] Step 2: Create a write-off relationship table (the write-off relationship table for multiple different document conversion rules can share the same table).

[0229] In data modeling, create a write-off relationship table, including key fields and storage logic as shown in Table 3:

[0230] Table 3

[0231]

[0232] Step 3: Configure document conversion rules:

[0233] Order Type: Select "Pull Generation".

[0234] Reference type: Select "Subtable references main table".

[0235] Source Document List: Configure the loan document list.

[0236] Write-off relationship table: bind write-off relationship table.

[0237] Write-off Amount field: This field contains the current write-off amount from the asset report loan write-off sub-table.

[0238] Step 4: Field matching:

[0239] Map the loan document main table fields (such as loan amount and loan purpose) to the asset report form sub-table.

[0240] Step 5: Parameter setting:

[0241] Allow multiple selections: If checked, multiple loan documents can be selected in the reference interface.

[0242] Cross-Document Definition Selection: If checked, the loan document and loan initial document can be selected at the same time in the reference interface.

[0243] Reference interface to query source document: Check this option, and the reference interface can open the loan document details interface by the loan document number.

[0244] Display the unwritten-off amount column on the reference interface: If checked, the reference interface will display the unwritten-off amount data of the loan document, making it easier for users to check the available amount.

[0245] Step 6: Reverse settings:

[0246] Update the "Cumulative Write-off Amount" field of the loan document and write back the current write-off amount in the asset report sub-table. The asset report references the cumulative write-off amount of the loan document and writes back the cumulative write-off amount of the loan document.

[0247] Step 7: Target single configuration:

[0248] Add a "Reference Loan" button (bill-ref) to the asset report toolbar and bind the "Asset Report Reference Loan Document" document conversion rule template.

[0249] The processing logic during the actual conversion process:

[0250] Step 1: The user opens an asset statement and clicks the "Reference Loan" button.

[0251] Step 2: The right drawer of the document interface displays the available loan data. The program first locates the table containing the loan document list based on the rule template bound to the button. It then filters the data based on the conditions configured on the query criteria tab and the presence of unwritten loans (loan amount - written-off amount in the write-off relationship table), and displays it in the right drawer.

[0252] In step 3, the user selects multiple loans eligible for write-off and clicks Confirm. The program then applies the field values ​​from the loan document to the fields in the asset report based on the field mappings configured on the Field Matching tab. For example, the organizational unit in the loan document master table is applied to the organizational unit in the asset report master table, and the loan amount is applied to the loan amount field in the loan write-off sub-table of the report.

[0253] Step 4. The user fills in the loan amount to be written off (field on the asset report). The loan order can be written off multiple times.

[0254] Step 5: The program stores the write-off relationship table. Based on the configured write-off relationship table, the program stores the write-off relationship table and writes back to the loan document, adding the current loan write-off amount to the "Cumulative Write-off Amount" field on the loan document. (If a loan document is written off multiple times, each write-off amount is added to the Write-off Amount.)

[0255] It is worth noting that the system automatically stores the write-off relationship: the ID is automatically generated, the loan document number is written into the target document number, the asset report number is written into the target document number, and the loan amount written off this time is written into the amount field of the write-off relationship table.

[0256] Step 6: Generate vouchers after asset report approval is completed.

[0257] It is worth noting that the acquisition, storage, use, and processing of data in the technical solutions of this application are in compliance with the relevant provisions of laws and regulations. The user information in the embodiments of this application is obtained through legal and compliant channels, and the acquisition, storage, use, and processing of user information are authorized and agreed by the customer.

[0258] It is worth noting that the information collected in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0259] It is worth noting that the technical solution provided in this application provides users with corresponding operation entrances for them to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.

[0260] In the technical solution of the universal conversion method of document data provided by the embodiment of the present invention, the business scenario analysis and rule field extraction of the acquired user input text are performed through the large model business flow processor and the intelligent body to generate a recommended rule template; the configuration field of the recommended rule template is updated according to the adjustment requirement text input by the user through the large model business flow processor to generate a target document conversion rule template; according to the target document conversion rule template, the source document data is subjected to universal data mapping conversion to generate a document data model of the target document, and dynamic code-free automatic configuration is achieved by configuring the document conversion rule template to improve reusability, which can meet the automatic conversion of homogeneous data and heterogeneous data to a universal document model in complex scenarios, shorten the delivery cycle, and reduce delivery costs; it can record multiple write-off relationships according to the write-off relationship table, support arbitrary revocation mechanism, reduce document redundancy, and improve the flexibility of write-off relationship processing in document conversion.

[0261] Figure 5 A schematic diagram of the structure of a document data universal conversion device provided by an embodiment of the present invention, the device is used to execute the above-mentioned document data universal conversion method, such as Figure 5 As shown, the device includes: a recommendation rule template generating unit 11, a target document conversion rule template generating unit 12 and a general data conversion unit 13.

[0262] The recommendation rule template generation unit 11 is used to perform business scenario analysis and rule field extraction on the acquired user input text through the large model business flow processor and the intelligent agent to generate a recommendation rule template.

[0263] The target document conversion rule template generating unit 12 is used to update the configuration fields of the recommended rule template according to the adjustment requirement text input by the user through the large model business flow processor, and generate the target document conversion rule template.

[0264] The general data conversion unit 13 is used to perform general data mapping conversion on the source document data according to the target document conversion rule template to generate a document data model of the target document.

[0265] In an embodiment of the present invention, the user input text is a multi-round dialogue text, which includes an intention description dialogue text and an information collection dialogue text; the recommended rule template generation unit 11 is specifically used to perform intent recognition on the intention description dialogue text through a large model business flow processor to generate an order type, source order information and target order information; perform scenario analysis on the information collection dialogue text through a large model business flow processor to generate a corresponding business scenario; the intelligent agent extracts the source order definition, target order definition and rule template configuration attributes through the document metadata interface and the document conversion metadata interface according to the order type, source order information and target order information; the large model business flow processor matches the business scenario, source order definition and target order definition according to the rule template configuration attributes to generate an initial rule template; the large model business flow processor supplements the fields of the initial rule template according to the preset rule template knowledge base to generate a recommended rule template.

[0266] In an embodiment of the present invention, the target document conversion rule template generation unit 12 is specifically used to identify the adjustment content of the adjustment requirement text through a large model business flow processor, where the adjustment content includes adjustment fields and corresponding field values; match the adjustment fields with the configuration fields of the recommended rule template to determine the configuration fields to be adjusted; update the configuration fields to be adjusted according to the field values, and update the recommended rule template according to the configuration fields to generate a target document conversion rule template.

[0267] In the embodiment of the present invention, the device further includes: a mapping unit 14.

[0268] The mapping unit 14 is used to set a document conversion rule template identifier for each target document conversion rule template, and match the document conversion rule template identifier with a business scenario to generate a mapping relationship between the business scenario and the document conversion rule template identifier.

[0269] In the embodiment of the present invention, the first template determining unit 15 .

[0270] The first template determination unit 15 is used to respond to the automatic order generation operation triggered by the planned task, and determine the target document conversion rule template according to the document conversion rule template identifier corresponding to the business scenario of the planned task. The business scenario corresponds to the order generation type, and the order generation type is pull generation or push generation.

[0271] In the embodiment of the present invention, the device further includes: a judgment unit 16 and a triggering unit 17 .

[0272] The judgment unit 16 is used to judge whether the document date and current time of the source document data meet the automatic document generation settings of the planned task; if not, continue to execute the judgment whether the document date and current time of the source document data meet the automatic document generation settings of the planned task.

[0273] The trigger unit 17 is used to trigger the automatic order generation operation if the conditions are met.

[0274] In an embodiment of the present invention, the target document conversion rule template includes field rule settings, reference types and parameter settings; the source document data includes homogeneous data or heterogeneous data; the general data conversion unit 13 is specifically used to perform format conversion and standardization encapsulation on heterogeneous data through the set document conversion adaptation facade, or to perform standardization encapsulation on homogeneous data to generate standardized source document data; according to the field rule settings and reference types, the standardized source document data is subjected to field mapping conversion to generate target table field data; according to the parameter settings, the target table field data is dimensionally processed to generate a document data model of the target document.

[0275] In the embodiment of the present invention, the target document conversion rule further includes basic information, and the basic information includes a write-off relationship table; the device further includes: a write-off relationship generating unit 18 .

[0276] The write-off relationship generating unit 18 is configured to generate a write-off relationship record according to the data model of the write-off relationship table, the standardized source document data, and the document data model of the target document.

[0277] In an embodiment of the present invention, the target document conversion rule further includes a reverse writing setting; the basic information further includes a cancellation control number; and the device further includes: a monitoring unit 19 , a verification unit 20 , an updating unit 21 and a reverse writing unit 22 .

[0278] The monitoring unit 19 is used to monitor events of the document model of the target document through the set document conversion event processor.

[0279] The verification unit 20 is used to verify the cancellation relationship record according to the cancellation control number if a save event is monitored.

[0280] The updating unit 21 is used to update the write-off relationship record to the write-off relationship table if the verification passes.

[0281] The reverse writing unit 22 is used to reverse write the source document data according to the reverse writing settings and the cancellation relationship records through the set document conversion reverse writing processor.

[0282] In the embodiment of the present invention, the apparatus further includes: a second template determining unit 23 , a rollback unit 24 and a releasing unit 25 .

[0283] The second template determining unit 23 is configured to determine a document conversion rule template corresponding to the document model of the target document if a deletion event is monitored.

[0284] The rollback unit 24 is used to perform a write-back rollback process on the source document data according to the write-back settings and cancellation relationship records in the determined document conversion rules through the set document conversion write-back processor.

[0285] The release unit 25 is used to delete the document data of the target document and release the write-off value in the write-off relationship record.

[0286] In the solution of the embodiment of the present invention, the business scenario analysis and rule field extraction of the acquired user input text are performed through the large model business flow processor and the intelligent agent to generate a recommended rule template; the recommended rule template is updated according to the configuration field input by the user through the intelligent agent to generate a target document conversion rule template; according to the target document conversion rule template, the source document data is converted into a general data mapping to generate a document data model of the target document, and dynamic code-free automatic configuration is achieved by configuring the document conversion rule template to improve reusability, which can meet the automatic conversion of homogeneous data and heterogeneous data to a general document model in complex scenarios, shorten the delivery cycle, and reduce delivery costs; it can record multiple write-off relationships according to the write-off relationship table, support arbitrary revocation mechanism, reduce document redundancy, and improve the flexibility of write-off relationship processing in document conversion.

[0287] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer device. Specifically, the computer device may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0288] An embodiment of the present invention provides a computer device including a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions. When the program instructions are loaded and executed by the processor, the steps of the embodiment of the above-mentioned general document data conversion method are implemented. For a specific description, please refer to the embodiment of the above-mentioned general document data conversion method.

[0289] Reference below Figure 6 , which shows a structural diagram of a computer device 600 suitable for implementing an embodiment of the present application.

[0290] like Figure 6As shown, computer device 600 includes a central processing unit (CPU) 601, which can perform various appropriate tasks and processes according to programs stored in a read-only memory (ROM) 602 or programs loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of computer device 600 are also stored in RAM 603. CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to bus 604.

[0291] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, mouse, and the like; an output section 607 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 608 including devices such as a hard disk; and a communication section 609 including a network interface card such as a LAN card or a modem. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. Removable media 611, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 610 as needed, so that computer programs read from the media can be installed in the storage section 608 as needed.

[0292] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program including program code for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication portion 609 and / or installed from removable media 611.

[0293] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can be implemented using any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0294] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0295] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0296] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0297] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0298] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0299] The acquisition, storage, use, and processing of data in this application's technical solution comply with relevant national laws and regulations.

[0300] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned. They should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0301] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0302] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0303] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0304] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A universal document data conversion method, characterized in that: The method comprises: Through the large-model business flow processor and intelligent agent, the business scenario of the acquired user input text is analyzed and the rule fields are extracted to generate the recommendation rule template; By means of the large model business flow processor, the configuration fields of the recommended rule template are updated according to the adjustment requirement text input by the user, and a target document conversion rule template is generated; Performing general data mapping conversion on the source document data according to the target document conversion rule template to generate the document data model of the target document; The user input text is a multi-round dialogue text, which includes an intention explanation dialogue text and an information collection dialogue text; The large model business flow processor and intelligent agent perform business scenario analysis and rule field extraction on the acquired user input text to generate a recommendation rule template, including: Through the large model business flow processor, the intention description dialogue text is recognized to generate the order type, source order information and target order information; Perform scenario analysis on the information collection dialogue text through the large model business flow processor to generate corresponding business scenarios; The intelligent agent extracts the source document definition, target document definition and rule template configuration attributes through the document metadata interface and the document conversion metadata interface according to the generation document type, source document information and target document information; By means of the large model business flow processor, the business scenario, source order definition and target order definition are matched according to the rule template configuration attributes to generate an initial rule template; The large model business flow processor supplements the fields of the initial rule template according to a preset rule template knowledge base to generate the recommended rule template.

2. The document data universal conversion method according to claim 1, characterized in that: The large model business flow processor updates the configuration fields of the recommended rule template according to the adjustment requirement text input by the user to generate a target document conversion rule template, including: Identifying, by the large model business flow processor, adjustment content of the adjustment request text, wherein the adjustment content includes adjustment fields and corresponding field values; Matching the adjustment field with the configuration field of the recommendation rule template to determine the configuration field to be adjusted; According to the field value, the configuration field to be adjusted is updated to generate the target document conversion rule template.

3. The document data universal conversion method according to claim 1, characterized in that: The method further comprises: A document conversion rule template identifier is set for each target document conversion rule template, and the document conversion rule template identifier is matched with a business scenario to generate a mapping relationship between the business scenario and the document conversion rule template identifier.

4. The universal document data conversion method according to claim 3, characterized in that: The method further comprises: In response to the automatic order generation operation triggered by the planned task, the target document conversion rule template is determined according to the document conversion rule template identifier corresponding to the business scenario of the planned task. The business scenario corresponds to an order generation type, and the order generation type is pull generation or push generation.

5. The universal document data conversion method according to claim 4, characterized in that: The method further comprises: Determine whether the document date and current time of the source document data conform to the automatic document generation settings of the planned task; If it meets the requirements, the automatic order generation operation will be triggered; If not, continue to execute the process of determining whether the document date and current time of the source document data comply with the automatic document generation settings of the planned task.

6. The universal document data conversion method according to claim 1, characterized in that: The target document conversion rule template includes field rule settings, reference types, and parameter settings; the source document data includes homogeneous data or heterogeneous data; The process of performing general data mapping conversion on the source document data according to the target document conversion rule template to generate the document data model of the target document includes: Through the document conversion adaptation facade, the heterogeneous data is formatted and standardized, or the homogeneous data is standardized and packaged to generate standardized source document data; According to the field rule settings and reference types, perform field mapping conversion on the standardized source document data to generate target table field data; According to the parameter settings, the target table field data is dimensionally processed to generate a document data model of the target document.

7. The universal document data conversion method according to claim 6, characterized in that: The target document conversion rule also includes basic information, and the basic information includes a write-off relationship table; After performing dimension processing on the target table field data according to the parameter settings to generate the document data model of the target document, the method further includes: According to the data model of the write-off relationship table, and based on the standardized source document data and the document data model of the target document, a write-off relationship record is generated.

8. The universal document data conversion method according to claim 7, characterized in that: The target document conversion rule also includes reverse writing settings; the basic information also includes a write-off control number; After generating the write-off relationship record according to the data model of the write-off relationship table and the standardized source document data and the document data model of the target document, the method further includes: Monitor events on the document model of the target document through the document conversion event handler that is set; If a save event is monitored, the write-off relationship record is verified according to the write-off control number; If the verification passes, the write-off relationship record is updated to the write-off relationship table; Through the document conversion rewrite processor that is set, the source document data is rewritten according to the rewrite setting and the write-off relationship record.

9. The universal document data conversion method according to claim 8, characterized in that: The method further comprises: If a deletion event is monitored, the document conversion rule template corresponding to the document model of the target document is determined; The document conversion and rewrite processor is configured to rewrite and roll back the source document data according to the rewrite settings and write-off relationship records in the determined document conversion rules; Delete the document data of the target document and release the write-off value in the write-off relationship record.

10. A universal document data conversion device, characterized in that: The device comprises: A recommendation rule template generation unit is used to parse the business scenario and extract the rule fields from the acquired user input text through a large model business flow processor and an intelligent agent to generate a recommendation rule template; A target document conversion rule template generating unit is configured to update the configuration fields of the recommended rule template according to the adjustment requirement text input by the user through the large model business flow processor to generate a target document conversion rule template; A general data conversion unit, configured to perform general data mapping conversion on the source document data according to the target document conversion rule template to generate a document data model of the target document; The user input text is a multi-round dialogue text, which includes an intention explanation dialogue text and an information collection dialogue text; The recommended rule template generation unit is specifically used to perform intent recognition on the intention description dialogue text through the large model business flow processor to generate the order type, source order information and target order information; perform scenario analysis on the information collection dialogue text through the large model business flow processor to generate the corresponding business scenario; extract the source order definition, target order definition and rule template configuration attributes through the document metadata interface and the document conversion metadata interface according to the order type, source order information and target order information through the intelligent agent; match the business scenario, source order definition and target order definition according to the rule template configuration attributes through the large model business flow processor to generate an initial rule template; supplement the fields of the initial rule template through the large model business flow processor according to the preset rule template knowledge base to generate the recommended rule template.

11. A computer-readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the universal document data conversion method described in any one of claims 1 to 9 is implemented.

12. A computer device comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, wherein: When the program instructions are loaded and executed by the processor, the universal document data conversion method described in any one of claims 1 to 9 is implemented.

13. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the universal document data conversion method according to any one of claims 1 to 9 is implemented.

Images