Document data general conversion method and device

Abstract

The invention provides a general document data conversion method and device, and the method comprises the steps: carrying out the business scene analysis and rule field extraction of an input text of a user through a large model business flow processor and an intelligent agent, generating a recommendation rule template, and carrying out the processing of the recommendation rule template; updating a configuration field of the recommendation rule template according to an adjustment requirement text input by a user to generate a target document conversion rule template; and according to the target document conversion rule template, performing general data mapping conversion on the source document data to generate a document data model of the target document, and realizing dynamic code-free automatic configuration by configuring the document conversion rule template, so that the reusability is improved, and the user experience is improved. Automatic conversion of isomorphic data and heterogeneous data to a general document model in a complex scene can be met, the delivery period is shortened, and the delivery cost is reduced; multiple cancel-after-verification relationships can be recorded according to the cancel-after-verification relationship table, an arbitrary cancel mechanism is supported, the bill redundancy is reduced, and the flexibility of cancel-after-verification relationship processing in bill conversion is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a general method and device for converting document data. Background Art

[0002] As a main discrete data collection component, documents are widely used in enterprise-level applications and carry a large amount of business process processing. Generally, there are a large number of upstream and downstream business transformation processes in enterprise-level applications. For example, in enterprise financial applications, there are businesses such as procurement, warehousing, settlement, and payment. Another example is business such as business trip applications and business trip reimbursements. The above-mentioned businesses all involve the reference, verification, and conversion processing between document businesses. In related technologies, usually according to the business scenario, by developing specific business reference buttons, the conversion of homogeneous data documents with corresponding business functions is realized. The scenarios of business functions are solidified. Once the business changes, it is necessary to re-develop the code to implement, and the delivery cycle is long and the delivery cost is high. In addition, when recording the reference and verification relationships between documents in related technologies, generally the method of writing back to the source document is used for processing, which requires adding additional control fields for recording reference relationships on the document, invading the business of the document, and the document redundancy is relatively high. In the scenario where the same document is repeatedly referenced and verified by multiple documents, the verification process cannot be accurately restored. When the target document is deleted or invalidated (reverse process), arbitrary revocation cannot be achieved, and the flexibility is relatively poor. Summary of the Invention

[0003] An object of the present invention is to provide a general method for converting document data, which realizes dynamic code-free automation configuration by configuring a document conversion rule template, improves reusability, and can meet the automatic conversion of homogeneous data and heterogeneous data to a general document model under complex scenarios, shortens the delivery cycle, and reduces the delivery cost; can record multiple verification relationships according to the verification relationship table, support an arbitrary revocation mechanism, reduce the document redundancy, and improve the flexibility of processing verification relationships in document conversion. Another object of the present invention is to provide a general device for converting document data. Still another object of the present invention is to provide a computer-readable medium. Yet another object of the present invention is to provide a computer device.

[0004] To achieve the above object, on the one hand, the present invention discloses a general method for converting document data, including:

[0005] Parsing the business scenario and extracting rule fields from the obtained user input text through a large model business flow processor and an intelligent agent to generate a recommended rule template;

[0006] Updating 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;

[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 conversation text, and the multi-round conversation text includes an intention description conversation text and an information collection conversation text;

[0009] Through the large model business flow processor and the intelligent agent, perform business scenario analysis and rule field extraction on the obtained user input text to generate a recommended rule template, including:

[0010] Through the large model business flow processor, perform intention recognition on the intention description conversation text to generate the order generation type, source document information, and target document information;

[0011] Through the large model business flow processor, perform scenario analysis on the information collection conversation text to generate the corresponding business scenario;

[0012] Through the intelligent agent, according to the order generation type, source document information, and target document information, respectively pass through the document metadata interface and the document conversion metadata interface to extract the source document definition, target document definition, and rule template configuration attributes;

[0013] Through the large model business flow processor, match the business scenario, source document definition, and target document definition according to the rule template configuration attributes to generate an initial rule template;

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

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

[0016] Through the large model business flow processor, identify the adjustment content of the adjustment requirement text, and the adjustment content includes the adjustment field and the corresponding field value;

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

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

[0019] Preferably, the method further includes:

[0020] Set a document conversion rule template identifier for each target document conversion rule template, and associate 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.

[0021] Preferably, the method further includes:

[0022] In response to the triggering of a scheduled task for automatic order generation operation, determine the target document conversion rule template according to the document conversion rule template identifier corresponding to the business scenario of the scheduled task. The business scenario corresponds to an order generation type, and the order generation type is pull generation or push generation.

[0023] Preferably, the method further includes:

[0024] Judge whether the document date of the source document data and the current time conform to the automatic order generation setting of the scheduled task;

[0025] If it conforms, trigger the automatic order generation operation;

[0026] If it does not conform, continue to judge whether the document date of the source document data and the current time conform to the automatic order generation setting of the scheduled 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 set document conversion adaptation facade, perform format conversion and standard encapsulation on the heterogeneous data, or perform standard encapsulation on the homogeneous data to generate the standardized source document data;

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

[0031] According to the parameter settings, perform dimensional processing on the target table field data 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 performing dimensional processing on the target table field data according to the parameter settings to generate the document data model of the target document, it further includes:

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

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

[0036] After generating write-off relationship records according to the data model of the write-off relationship table, based on the standardized source document data and the document data model of the target document, it further includes:

[0037] Through the set document conversion event processor, event listening is performed on the document model of the target document;

[0038] If a save event is monitored, the write-off relationship records are verified according to the write-off control numbers;

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

[0040] Through the set document conversion reverse write processor, according to the reverse write settings, the source document data is reverse written according to the write-off relationship records.

[0041] Preferably, the method further includes:

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

[0043] Through the set document conversion reverse write processor, according to the reverse write settings in the determined document conversion rules and the write-off relationship records, the source document data is reverse written and rolled back;

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

[0045] The present invention also discloses a general document data conversion device, including:

[0046] A recommended rule template generation unit for parsing the business scenario and extracting rule fields from the obtained user input text through a large model business flow processor and an intelligent agent to generate a recommended rule template;

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

[0048] A general data conversion unit for 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.

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

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

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

[0061] To facilitate the understanding of the technical solutions provided in this application, the relevant content of the technical solutions in this application will be described first. A document is an abstract data model, business model, and business component, which is used to process discrete business data collection, review, and other operations related to forms. The document data model generally has a main table and one or more sub-tables, corresponding to the main information and detailed (row) information of the document respectively. Common documents include, for example, leave applications, borrowing forms, business trip applications, expense reimbursement forms, etc. The present invention can efficiently achieve the automatic conversion between source document and target document data by developing a general document conversion system. Specifically, it can realize the mapping 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 in different business scenarios; the general document conversion system can meet scenarios such as pull-based generation and push-based generation, including but not limited to automatically performing data matching and conversion at regular intervals; it can support the reference / generation relationships between the main table and the sub-tables, including but not limited to: "main references main", "sub references main", and "sub references sub", and needs to support combined conversion according to the set dimension combinations; after the conversion is completed, it can automatically record the cancellation relationship, perform cancellation control, and provide a mechanism for backwriting the source document data; the document conversion rule templates can be dynamically configured without code to form conversion rule templates for reuse, supporting both the design period and the runtime state, which is convenient for business personnel to perform customized configuration; the general conversion of document data needs to cooperate with document design and operation, and provide corresponding encapsulated plugins, actions, interfaces, etc., to achieve out-of-the-box use.

[0062] Figure 1 The following is a schematic structural diagram of a general document data conversion system provided in an embodiment of the present invention, as Figure 1 shown. This system adopts a layered architecture design, including a runtime layer and a design period layer for front-end applications, and a model layer and an adaptation layer for back-end rule processing.

[0063] The runtime layer mainly provides an interaction entry for user interaction. The interaction entry is a series of interface operation buttons, interfaces, and scheduled tasks, etc., specifically including but not limited to pull-based document generation actions, pull-based input controls, pull-based document plugins, pull-based reference interfaces, push-based document generation actions, and push-based scheduled tasks. Users can trigger the general conversion of document data by clicking on the above interaction entries on the interface.

[0064] The design phase mainly provides the ability for business personnel to configure and publish the document conversion rule templates for implementation. According to different business scenarios, customized configuration of pull-generated rule templates or push-generated rule templates can be carried out, which are used for the front-end document business processing of users. Figure 2 It is a schematic structural diagram of a document conversion rule template provided by an embodiment of the present invention, as Figure 2 shown. The 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. The basic information includes document generation type, reference type, source document information, target document information, write-off control number, and write-off relationship table. The document generation type includes pull generation or push generation, and the reference type includes main reference to main, sub-reference to main, or sub-reference to sub. The field rule settings include query conditions and field mapping. The query conditions are to fill in the fields to be queried, and the field mapping includes the mapping relationship between the source document main table and the target document main table, the mapping relationship between the source document sub-table and the target document sub-table, and the mapping relationship between the source document main table and the target sub-table; the reverse writing settings include reverse writing field mapping and reverse writing timing; the parameter settings include reference interface parameters, document generation execution parameters, and document generation save parameters. The document generation execution parameters include summary dimension, summary indicator, or document generation dimension, and the document generation save parameters include combined document generation or item-by-item document generation. The automatic document generation settings include document generation timing, document generation conditions, and document generation dimension. The document generation timing is the trigger document generation timing that can be set, for example: the difference between the system date and the document date is 1; the document generation conditions are the document generation conditions that can be set, for example: when the source document is saved, when the process approval is completed; the document generation dimension is the table field reference.

[0065] The model layer includes a document conversion rule processing model, a general main table data model, a general sub-table data model, a dimension mapping data model, a write-off relationship table data model, a document conversion adaptation facade, a document conversion reverse writing processor, and a document conversion event processor. The document conversion rule processing model can parse the document conversion rule template defined in the design phase and provide it for the adaptation layer to use; the processing adaptation facade receives the source document data according to the document conversion rule template and converts it into a general main table data model and a general sub-table data model; based on the converted document data model, combined with the document conversion rule template, according to the dimension mapping data model and the write-off relationship data model, processing such as dimension summarization and write-off relationship update is carried out. The document conversion adaptation facade is used to encapsulate the adapter interface specifications of various source document data types for the lower adaptation layer and register and collect the implemented adapters; the document conversion reverse writing processor provides a reverse writing processing mechanism for the source document data, which is used to reverse write the write-off relationship records of the write-off relationship table to the source document data; the document conversion event processor is used to listen for the save or delete events of the document model of the target document and process the document data model of the target document, the corresponding write-off relationship table, and the source document data based on different listening events.

[0066] The adaptation layer mainly consists of data adapters registered by the source single data party. The built-in adapters include, but are not limited to, document data adapters, report data adapters, query data adapters, and other data adapters. The source data (homogeneous data or heterogeneous data) is adapted according to the document conversion rule template, and the adapted data is sent to the document conversion adaptation facade in the model layer for the document conversion rule model to convert the data received by the document conversion adaptation facade into a general master table data model and a general sub-table data model.

[0067] In the technical solution provided by the embodiment of the present invention, through the large model business flow processor and the intelligent agent, the business scenario of the obtained user input text is parsed and the rule fields are extracted to generate a recommended rule template; through the intelligent agent, the recommended rule template is updated according to the configuration fields 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 subjected to general data mapping conversion to generate the document data model of the target document. By configuring the document conversion rule template, dynamic code-free automation configuration is realized, the reusability is improved, and the automatic conversion of homogeneous data and heterogeneous data to the general document model under complex scenarios can be satisfied, shortening the delivery cycle and reducing the delivery cost; the multiple write-off relationships can be recorded according to the write-off relationship table, any cancellation mechanism is supported, the document redundancy is reduced, and the flexibility of the write-off relationship processing in document conversion is improved.

[0068] It should be noted that Figure 1 the general document data conversion system shown is also applicable to Figure 3 or Figure 4 the general document data conversion method, which will not be elaborated here.

[0069] Taking the general document data conversion device as the execution subject as an example below, the implementation process of the general document data conversion method provided by the embodiment of the present invention is described. It can be understood that the execution subject of the general document data conversion method provided by the embodiment of the present invention includes, but is not limited to, the general document data conversion device.

[0070] Figure 3 It is a flowchart of a general document data conversion method provided by an embodiment of the present invention. As Figure 3 shown, the method includes:

[0071] Step 101: Through the large model business flow processor and the intelligent agent (Agent), the business scenario of the obtained user input text is parsed and the rule fields are extracted to generate a recommended 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 description dialogue text and information collection dialogue text.

[0073] In an embodiment of the present invention, the large model business process processor is a pre-trained model for orchestrating business processes, with natural language processing (NLP) capabilities. For multi-turn dialogue texts, pre-trained language models such as BERT and Transformer can be injected to understand user inputs and perform functions such as intent recognition and scenario analysis. It also has the function of a rule engine to automate business processes, allowing the definition of clear business rules for 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 is the execution unit in the entire system, responsible for completing specific tasks according to the guidance of the large model business process orchestration, including but not limited to: interacting with the document conversion rule template service to synchronize necessary metadata information; extracting corresponding data information from source document information and target document information; calling the encapsulated document conversion metadata interface (API) and document metadata API to generate results based on the rule template recommendations provided by the large model business process orchestration, and generating specific rule definitions; and completing operations such as creating, validating, saving, and publishing the target document conversion rule template by calling various APIs provided by the document conversion rule template service (such as new / temporary save API, validation / save API, publish API, etc.).

[0075] It should be noted that each API is encapsulated according to the Model Context Protocol (abbreviated as: MCP) and provided for the Agent or the large model business process processor to call.

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

[0077] In an embodiment of the present invention, the user can be asked about the places that need to be adjusted so that the user can output the adjustment requirement text. The adjustment requirement text is the content that the user needs to modify, add, delete, or update the recommended rule template according to actual needs. The configuration field is the field to be adjusted parsed from the adjustment requirement text.

[0078] As another alternative, analyze the document conversion business scenario to be implemented. First, determine the document generation type and reference type to be adopted, and then configure and debug one by one according to the general template to complete the configuration of the corresponding conversion rules and the release of the target document conversion rule template.

[0079] In the embodiments 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. The basic information includes document generation type, reference type, source document information, target document information, write-off control number, and write-off relationship table.

[0080] The document generation type includes pull generation or push generation. Pull generation is a way to generate the data of the source document to the target document on the target document by referring to the source document. Push generation is a way to generate the data of the source document to the target document by actively generating the target document on the source document.

[0081] The reference type includes main reference to main, sub-reference to main, or sub-reference to sub. Main reference to main means that the main table of the target document refers to the main table of the source document, generally referring to the number of the source document to establish a business write-off relationship and joint query. Sub-reference to main means that the sub-table of the target document refers to multiple main tables of the source document to generate the sub-table row information of the target document (which can be combined and summarized by dimension) to establish a business write-off relationship and joint query. Sub-reference to sub means that the sub-table of the target document refers to the sub-table row information of at least one sub-table of the source document to generate the sub-table row information of the target document (which can be combined and summarized by dimension) to establish a business write-off relationship and joint query, and supports referring to the sub-table information of multiple source documents to the target document at one time.

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

[0083] Further, the document conversion also supports the combination of mapping methods. Specifically, in pull generation, the mapping method of sub-reference to main also includes that both the main table and the sub-table of the target document refer to multiple main tables of the source document; the mapping method of sub-reference to sub also includes that both the main table and the sub-table of the target document refer to multiple main tables of the source document, and both the main table and the sub-table of the target document refer to multiple sub-tables of the source document. Specifically, in push generation, the mapping method of sub-reference to main also includes that both the main table and the sub-table of the target document refer to multiple main tables of the source document; the mapping method of sub-reference to sub also includes that both the main table and the sub-table of the target document refer to multiple main tables of the source document, and both the main table and the sub-table of the target document refer to multiple sub-tables of the source document.

[0084] The source document information is the basic information of the source document data, including but not limited to the source document number, source document definition, source document sub-table ID, and source document main table ID. The source document is the original initiated document or data record in the business process, usually the starting point or basis of business processing. For example: when reimbursing, an application must be made first and then reimbursed. In the relationship between the reimbursement form and the application form, the application form is the source document.

[0085] The target order information is the basic information of the target order data, including but not limited to the target order number, target order definition, target order main table ID, and target order sub-table ID. The target order is a new document generated based on the source document (document or data record) in the business process and is usually the business object for subsequent business processing. For example, when applying for reimbursement, an application must be submitted first, and in the relationship between the reimbursement form and the application form, the reimbursement form is the target order.

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

[0087] The write-off control number is the upper limit for the source document to be referenced by the target order (or to generate the target order), and it controls the total amount of repeated reference (generation) of the source document. As an optional solution, the control number is the amount or quantity of the source document.

[0088] The write-off relationship table is a set of write-off records used to record the corresponding relationship of the referenced (generated) data between the target order and the source document. The write-off records include but not limited to row representation, target order number, target order definition, target order main table ID, target order 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 identifier.

[0089] It should be noted that the source document must have a source document number, so there is no need to redundantly store the source document main table ID, which saves space; since the document number of the target order may be generated only when saving (only the target order ID exists when creating), it is necessary to record the target order ID first and then update the target order number when the target order is saved.

[0090] Step 103: 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 order.

[0091] In the embodiment of the present invention, the target document conversion rule template further includes field rule settings and parameter settings; the source document data includes homogeneous data or heterogeneous data. Specifically, according to the field rule settings and parameter settings, perform general data mapping conversion on the homogeneous data or heterogeneous data to generate the document data model of the target order.

[0092] In the technical solution provided by the embodiment of the present invention, through the large model business flow processor and the intelligent agent, the obtained user input text is subjected to business scenario parsing and rule field extraction to generate a recommendation rule template; through the intelligent agent, the recommendation rule template is updated according to the configuration fields 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 subjected to general data mapping conversion to generate the document data model of the target document. By configuring the document conversion rule template, dynamic code-free automation configuration is realized, the reusability is improved, and it can meet the automatic conversion of homogeneous data and heterogeneous data into a general document model under complex scenarios, shorten the delivery cycle, and reduce the delivery cost; it can record multiple write-off relationships according to the write-off relationship table, support any cancellation mechanism, reduce the document redundancy, and improve the flexibility of write-off relationship processing in document conversion.

[0093] Figure 4 It is a flowchart of another general method for document data conversion provided by the embodiment of the present invention, as Figure 4 shown, and this method includes:

[0094] Step 201, through the large model business flow processor and the intelligent agent, perform business scenario parsing and rule field extraction on the obtained user input text to generate a recommendation rule template.

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

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

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

[0098] It should be noted that the intent description dialogue text related to the source document information and the target document information can be elicited by asking the user questions about the documents to be processed and the document generation type.

[0099] Step 2012, through the large model business flow processor, perform scenario parsing on the information collection dialogue text to generate the corresponding business scenario.

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

[0101] It should be noted that the information collection dialogue text related to the business scenario can be elicited by asking the user questions about the specific application scenarios of document conversion.

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

[0103] In the embodiment of the present invention, the Agent obtains the rule template configuration attributes by calling the document conversion metadata API. The rule template configuration attributes can be the rule template configuration attributes corresponding to the document generation 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: 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 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 rule between the source document and the target document, and establishes the basic information under the document conversion rule template to generate an initial rule template.

[0106] Step 2015: 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.

[0107] In the embodiment of the present invention, the rule template knowledge base stores various document conversion rule templates and the basic information, field mapping rule settings, reverse 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, and fills the corresponding field mapping rule settings, reverse writing settings, parameter settings, and automatic document generation settings into the initial rule template to generate a recommended rule template.

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

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

[0111] In the embodiment of the present invention, the large model business process processor identifies the adjustment content of the adjustment requirement text through the NLP model. The adjustment content includes the adjustment fields and the 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 to generate an updated recommended rule template; visually display the updated recommended rule template to the user and ask the user whether to modify the recommended rule template. If the user inputs 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 input the adjustment requirement text, determine the updated recommended rule template as the target document conversion rule template.

[0112] Further, by asking the user whether to confirm the release of the target document conversion rule template, options such as new / temporary save, verification / save, and release can be provided; in response to the new / temporary save option, the Agent calls the rule template new / temporary save API to create / temporarily save 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 associate 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 determine the corresponding document conversion rule template, and establish a correspondence relationship among the business scenario, the document conversion rule template identifier, and the target document conversion rule template.

[0115] It should be noted 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 should be noted that in subsequent actual applications, if the user needs to create a new target document conversion rule template, the process from step 201 to step 20 can be executed; if the user needs to call the target document conversion rule template in a historical business scenario, the target document conversion rule template corresponding to the historical business scenario or document conversion rule template identifier can be directly called. Further, the user can adaptively modify the called target document conversion rule template according to actual needs. This calling method can improve the reuse rate of the document conversion rule template, reduce costs, improve the degree of automation and document conversion efficiency.

[0117] Through the collaborative work of the large model business flow processor and the Agent intelligent agent, the present invention realizes the automatic parsing of user input text and the generation of rule templates, significantly improving the efficiency and intelligence level of document conversion configuration. Through configurable field mapping, reverse writing mechanism and multi-time trigger capabilities, the adaptability of the system to complex business scenarios is enhanced, and the flexibility and data consistency of document verification processing are improved. At the same time, it supports the rapid reuse and adjustment of historical rule templates, effectively reducing the redundant configuration cost and improving the overall business processing efficiency and automation ability.

[0118] Step 204: Determine whether the document date of the source document data and the current time meet the automatic document generation setting of the scheduled task. If they meet, execute step 205; if not, repeat step 204.

[0119] In the embodiments of the present invention, each step is executed by a general document data conversion device.

[0120] In the embodiments 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] Taking the automatic document generation setting of the scheduled task as the document generation condition as an example, the document generation condition is that the document date is the day before the current time. If the document date of the source document data is the day before the current time, it means that the document date of the source document data and the current time meet the automatic document generation setting of the scheduled task, triggering the automatic document generation operation of the scheduled task, and continuing to execute step 205; if the document date of the source document data is not the day before the current time, it means that the document date of the source document data and the current time do not meet the automatic document generation setting of the scheduled task, and the automatic document generation operation of the scheduled task will not be triggered, and step 204 will continue to be executed for judgment until the automatic document generation setting is met.

[0122] It should be noted that the automatic document generation setting can be set according to actual needs, and the embodiments of the present invention do not limit this. The automatic document generation setting is configured in the scheduled task and bound to the target document conversion rule template identifier corresponding to the current business scenario.

[0123] As another alternative, the business personnel can manually trigger the operation of generating documents for the business scenario. For pull generation, a document generation action or an input control is configured in the target document, and the template identifier of the target document conversion rule corresponding to the current business scenario is bound; for push generation, a document generation action is configured in the source document or the source document list, and the template identifier of the target document conversion rule corresponding to the current business scenario is bound.

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

[0125] In the embodiment of the present invention, the business scenario corresponds to a document generation type, and the document generation type is pull generation or push generation. The difference between pull generation and push generation lies in whether the starting point of the operation initiation is the source document or the target document. Pull generation is initiated from the target document, and push generation is initiated from the source document.

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

[0127] It should be noted that the business personnel can select and configure according to different complex scenarios in the document conversion rule template, and can configure the document conversion rule template that meets various business scenarios without code development, improving the template delivery efficiency, thereby enhancing the document conversion processing efficiency, and greatly enhancing the response efficiency of business consultants to business scenario requirements.

[0128] Step 206: Through the set document conversion adaptation facade, perform format conversion and standard encapsulation on heterogeneous data, or perform standard encapsulation on homogeneous data to generate standardized source document data.

[0129] In the embodiment of the present invention, the document adaptation facade adopts the facade design pattern (Façade Pattern), mainly to simplify the access interfaces between the document conversion rule processing model and various data adapters. Various data adapters implement a unified facade interface to ensure the stability of the model layer. The facade design pattern provides a simplified unified interface for a complex system or a group of complex interfaces, hiding the complexity of the system 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 specification to generate standardized source document data; or encapsulates the homogeneous data according to the preset encapsulation specification to generate standardized source document data.

[0131] By introducing the facade design pattern, the model layer in the present invention only depends on the facade interface and does not need to care about the implementation details of the underlying specific adapters, reducing the coupling degree; the newly added adapter only needs to implement the standard interface without affecting the existing business logic, improving the maintainability and scalability; by uniformly controlling the adaptation process in the model layer, frequent modifications caused by underlying changes are avoided, enhancing the system stability; a consistent call entry is provided, reducing duplicate code, standardizing the interaction process between systems, and improving the development efficiency.

[0132] Step 207: According to the field rules setting and reference type, perform field mapping conversion on the standardized source document data to generate target table field data.

[0133] In the embodiment of the present invention, the field rules 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 document main table and the target document main table, the mapping relationship between the source document sub-table and the target document sub-table, and the mapping relationship between the source document main table and the target sub-table.

[0134] Specifically, if the reference type is main reference to main, according to the mapping relationship between the source document main table and the target document main table, perform field mapping conversion on the fields of the source document main table in the standardized source document data to generate target main table field data.

[0135] If the reference type is sub-reference to sub, according to the mapping relationship between the source document sub-table and the target document sub-table, perform field mapping conversion on the fields of the source document sub-table in the standardized source document data to generate target sub-table field data.

[0136] If the reference type is sub-reference to main, according to the mapping relationship between the source document main table and the target sub-table, perform field mapping conversion on the fields of the source document main table in the standardized source document data to generate target sub-table field data.

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

[0138] Step 208: According to the parameter settings, perform dimensional processing on the target table field data to generate the document data model of the target document.

[0139] In the embodiment of the present invention, the parameter settings include reference interface parameters, document generation execution parameters, and document generation save parameters. The reference interface parameters include, but are not limited to, allowing multiple selections, allowing cross-document definition selections, reference interface associated query of source documents, and displaying unwritten-off amounts. The document generation execution parameters include, but are not limited to, summary dimensions, summary indicators, or document generation dimensions. The document generation save parameters include, but are not limited to, merged document generation or individual document generation.

[0140] Specifically, according to the reference interface parameters, order generation execution parameters, and order generation save parameters, the target table field data is dimensionally split, combined, and summarized to generate the document data model of the target document. For example, the reference interface parameters include: allow multiple selections: whether the reference interface list data can be selected multiple times; allow cross-document definition selection: whether the source document data of different types of documents can be selected simultaneously; reference interface associated query of source document: whether the reference interface list data can penetrate and query the source document details through the document number column; display unwritten-off amount: whether to display the remaining unwritten-off amount of the source document. The order generation execution parameter is the summarization dimension, and the summarization dimension is the department dimension. The order generation dimension is to generate only one summarization row for the same department, and the target table field data is processed according to the department dimension to generate the document data model of the target document.

[0141] In the embodiment of the present invention, merged order generation or individual order generation is available in the push generation mode. Merged order generation is to push multiple source documents to generate one target document; individual order generation is to respond to the order generation dimension and summarization indicators, and generate multiple target documents according to the configured dimension.

[0142] Step 209: According to the data model of the write-off relationship table, generate a write-off relationship record based on 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 the 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 and the current write-off value of the current conversion. Specifically, according to the source document number, source document definition, source document sub-table ID in the standardized source document data, the target document number, target document definition, target document main table ID, target document sub-table ID, current write-off value, and document conversion rule template identifier in the document data model of the target document, a new write-off relationship record is generated.

[0147] It should be noted that the source document must have a source document number, so there is no need to redundantly store the source document main table ID. Since the document number of the target document may be generated only when saving (only the target document main table ID and target document sub-table ID exist when creating), it is necessary to first record the target document main table ID and target document sub-table ID, and then update the target document number when the target document is saved.

[0148] Step 210: Through the set document conversion event processor, perform event monitoring on the document model of the target document. If a save event is monitored, execute Step 211; if a delete event is monitored, execute Step 214.

[0149] In the embodiments of the present invention, the document model includes, but is not limited to, a document data model, corresponding model conversion rules, and model actions. The document conversion event processor is used to listen for all events on the document model. The model conversion rules are the rules in the document conversion rule template corresponding to the document data model, and the model actions are the actions performed by the document data model.

[0150] In the embodiments of the present invention, the document conversion event processor continuously listens for the document model of the target document. The listened events include save events and delete (revoke) events. If a save event is listened, it indicates that the document data model of the target document needs to be saved, and step 211 is continued. If a delete (revoke) event is listened, it indicates that the document data model of the target document needs to be deleted, and step 214 is continued.

[0151] Step 211: Check the write-off relationship record according to the write-off control number. If the check passes, step 212 is executed. If the check fails, the process ends.

[0152] In the embodiments of the present invention, the write-off control number is the upper limit for the source document to be referenced (or generate the target document) by the target document, and it performs the total control of the repeated reference (generation) of the source document. As an alternative, the write-off control number is 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 upper limit of reference / generation has not been exceeded, the check 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 upper limit of reference / generation has been exceeded, the check fails, and the process ends.

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

[0155] In the embodiments of the present invention, if the document number of the target document is generated during saving, the document number of the target document in the write-off relationship record is also updated. The updated write-off relationship record is added to the write-off relationship table to update the write-off relationship table.

[0156] Step 213: Through the set document conversion reverse write processor, according to the reverse write settings, reverse write the source document data according to the write-off relationship record, and the process ends.

[0157] In the embodiments of the present invention, the reverse write settings include reverse write field mapping and reverse write timing. The reverse write field mapping is to configure the mapping relationship between the fields that need to be reverse written in the source document and their values. Generally, the value mapping is to the fields of the target document. During the reverse write execution, the target document fields are written back to the source document fields. For example: the reimbursement amount of the asset reimbursement bill (target document) is written back to the accumulated written-off amount field of the borrowing bill (source document).

[0158] It should be noted that the backwriting timing can be set according to actual requirements. The default timing for actual backwriting is when the target order save event is monitored, and when the target order deletion (abandonment) event is monitored.

[0159] For example, the source order data also includes a verification status, and the field type of the verification status is a boolean type, indicating whether the source order has been verified. If a save event of the document model of the target order occurs, after updating the verification relationship table, the verification status of the source order data is backwritten and updated to verified.

[0160] It should be noted that other business fields that need to be backwritten and updated in the source order data can also be configured. The specific business fields can be set according to actual requirements, and the embodiments of the present invention do not limit this. The backwriting and updating methods include overwriting or accumulation (subtraction).

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

[0162] In the embodiments of the present invention, based on the verification relationship table, according to the target order number of the document data model of the target order, the corresponding document conversion rule template identifier is determined; 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 order, the determined document conversion rule template is traversed to determine the fields that need to be backwritten.

[0163] Step 215: Through the set document conversion backwriting processor, perform backwriting and rollback processing on the source order data according to the backwriting settings and verification relationship records in the determined document conversion rules.

[0164] In the embodiments of the present invention, the backwriting settings include backwriting field mapping and backwriting timing. The backwriting field mapping is to configure the mapping relationship between the fields that need to be backwritten in the source order and their values. Generally, the value mapping is the field of the target order, and when backwriting is executed, the target order field is written back to the source order field. For example: the reimbursement amount of the asset reimbursement bill (target order) is backwritten to the cumulative verified amount field of the borrowing order (source order).

[0165] It should be noted that the backwriting timing can be set according to actual requirements. The default timing for actual backwriting is when the target order save event is monitored, and when the target order deletion (abandonment) event is monitored.

[0166] For example, the source order data also includes a verification status, and the field type of the verification status is a boolean type, indicating whether the source order has been verified. If a delete / abandonment event of the document model of the target order occurs, after updating the verification relationship table, the verification status of the source order data is backwritten and rolled back to unverified.

[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: Store the write-off relationship to ensure the traceability of the correspondence between bank statements and the sub-table of receipt vouchers.

[0180] Timing of generating documents: Batch select multiple records in the bank statement list and manually trigger through the push-generated button.

[0181] Condition for generating documents: Bank statements with a document date one day before the system time.

[0182] The configuration steps are as follows:

[0183] Step 1: Create a bank statement document list and a write-off relationship table. The key fields and field storage logics included in the write-off relationship table are shown in Table 2:

[0184] Table 2

[0185]

[0186] Step 2: Configure the document conversion rules:

[0187] Type of generating documents: Select "Push generation".

[0188] Reference type: Select "Sub-table references the main table" (sub-reference main).

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

[0190] Step 3: Field matching:

[0191] Configure the sub-table field mapping, that is: Map the bank statement main table information to the receipt voucher sub-table statement information.

[0192] Step 4: Reverse writing setting:

[0193] The reverse writing setting is an optional item. If it is necessary to update the reference status of bank statement documents, configure the reverse writing fields. After the bank statement is pushed to generate a receipt voucher, assign the reference status of the bank statement to "already referenced". In the bank statement list, the bank statement information that has been referenced can be queried through the reference status.

[0194] Step 5: Automatic document generation:

[0195] Generating timing: Scheduled task, trigger automatic document generation through the scheduled task regularly. Configure the automatic document generation scheduled task, regularly check the bank statements that meet the document generation conditions in the automatic document generation and have not been processed, and push to generate receipt vouchers.

[0196] Generating conditions: Document date of the main table = system date - 1. When the scheduled task is executed, the bank statement documents with a document date one day before the current system time will be automatically generated into receipt vouchers, and the bank statement documents that do not meet this condition will not generate receipt vouchers.

[0197] Single generation dimension: Set as the organizational structure field of the main table. When the planned task is executed, bank statement documents with the same organizational structure will be generated into the sub-table of the same receipt note, and bank statement documents with different organizational structures will be generated into different receipt notes.

[0198] Processing logic in the actual conversion process:

[0199] First step, the system is regularly executed through the execution cycle of the configured planned task.

[0200] Second step, when executing, 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 receipt note has been generated (no record in the write-off relationship).

[0201] Third step, group and generate documents for the filtered data according to the document generation dimension (organizational structure of the main table) in the automatic document generation configuration, that is, data with the same organizational structure in the bank statement list is generated onto one receipt note.

[0202] Fourth step, bring the fields of the bank statement into the main and sub-tables of the single receipt note according to the field matching rules in the configuration. For example, the organizational structure of the bank statement main table is brought into the organizational structure of the receipt note main table, and the bank account number of the bank statement is brought into the bank account number field of the receipt note sub-table, etc.

[0203] Fifth step, after bringing in, the system automatically saves the receipt note, the program stores the write-off relationship table and writes back to the bank statement, and updates the source document status field to "already referenced".

[0204] Note: The system automatically stores the write-off relationship: The receipt note ID is automatically generated, the receipt note 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] Sixth step, the receipt note completes the process approval to generate vouchers.

[0206] The following uses a specific pull generation example to describe the general conversion process of document data. Taking the example of the asset reimbursement form of the XX project referencing the loan note data.

[0207] Business scenario description:

[0208] The asset module reimbursement form needs to reference the personal loan note and write off the personal loan. Realize the association between asset reimbursement and personal loan, ensure the clarity of the fund usage, help the enterprise control the loan usage and ensure the timely write-off of personal loans.

[0209] Related accounting treatment:

[0210] When a personal loan occurs:

[0211] Debit: Imprest - Personal Loan.

[0212] Credit: Bank Deposit.

[0213] When the assets are reported for reimbursement:

[0214] Debit: Fixed Assets.

[0215] Credit: Bank Deposit.

[0216] Credit: Imprest - Personal Loan.

[0217] Business Logic:

[0218] Document Generation Type: Pull Generation (manually triggered by the user).

[0219] Reference Relationship: The sub - table references the main table, that is, the data in the sub - table of the asset reimbursement form is sourced from the main table data of the loan form.

[0220] Write - off Relationship: Store the write - off relationship to ensure the traceability of the correspondence between the loan form and the asset reimbursement form.

[0221] Parameter Settings:

[0222] Multiple selection of loan forms is allowed.

[0223] Cross - document definition selection is supported.

[0224] The un - written - off amount column is displayed in the reference interface for easy verification by the user.

[0225] Source document joint query is supported to improve operation convenience.

[0226] Configuration Steps:

[0227] Step 1: Create a list of loan form documents.

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

[0229] Create a write - off relationship table in data modeling. The key fields included are stored as shown in Table 3:

[0230] Table 3

[0231]

[0232] Step 3: Configure the document conversion rules:

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

[0234] Reference Type: Select "Sub - table references the main table".

[0235] Source Document List: Configure the list of loan form documents.

[0236] Write-off relationship table: Bind the write-off relationship table.

[0237] Write-off amount field: The current write-off amount in the sub-table of the asset reimbursement form for loan write-off.

[0238] Fourth step, field matching:

[0239] Map the fields in the main table of the loan form (such as loan amount, loan purpose) to the sub-table of the asset reimbursement form.

[0240] Fifth step, parameter setting:

[0241] Allow multiple selections: Check the box, and multiple loan forms can be selected in the reference interface.

[0242] Cross-document definition selection: Check the box, and both loan forms and initial loan forms can be selected simultaneously in the reference interface.

[0243] Linked query of source documents in the reference interface: Check the box, and the detailed loan form interface can be opened through the loan form document number in the reference interface.

[0244] Display the unwritten-off amount column in the reference interface: Check the box, and the unwritten-off amount data of the loan form is displayed in the reference interface to facilitate users to check the available amount.

[0245] Sixth step, reverse write setting:

[0246] Update the "accumulative written-off amount" field in the reverse write configuration loan form, overwrite the reverse write with the current write-off amount in the sub-table of the asset reimbursement form, and accumulate and reverse write the write-off amount of each time the asset reimbursement form references the loan form to update the accumulative written-off amount of the loan form.

[0247] Seventh step, target form configuration:

[0248] Add a "Reference Loan" button (bill-ref) to the toolbar of the asset reimbursement form, and bind the document conversion rule template of "Asset Reimbursement Form References Loan Form".

[0249] Processing logic in the actual conversion process:

[0250] First step, the user opens an asset reimbursement form and clicks the "Reference Loan" button.

[0251] Second step, the right-side drawer of the document interface displays the loan data that can be referenced. The program first finds the data table where the loan form document list is located according to the rule template bound by the button. Then, the data is filtered according to the conditions configured in the query condition tab and the existence of unwritten-off loans (loan amount - write-off amount in the write-off relationship table) and displayed in the right-side drawer.

[0252] Step 3: The user checks multiple loans that can be written off and clicks the confirmation button. The program brings the field values on the loan note to the fields on the asset bill according to the field mapping set in the field matching tab. For example, the organization in the main table of the loan note is brought to the organization in the main table of the asset bill, and the loan amount is brought to the loan amount field in the loan write-off sub-table of the bill, etc.

[0253] Step 4: The user fills in the loan amount to be written off this time (the field on the asset bill), and the loan note can be written off multiple times.

[0254] Step 5: The program stores the write-off relationship table. According to the configured write-off relationship table, the program stores the write-off relationship table and writes back to the loan note document, adding the current loan write-off amount to the "accumulative written-off amount" field of the loan note (when the loan note is written off multiple times, each current write-off amount is added to the written-off amount).

[0255] It should be noted that the system automatically stores the write-off relationship: the ID is automatically generated, the loan note number is written into the target document number, the asset bill number is written into the target document number, and the current loan write-off amount is written into the amount field of the write-off relationship table.

[0256] Step 6: Generate vouchers after the approval of the asset bill is completed.

[0257] It should be noted that in the technical solution of this application, the acquisition, storage, use, processing, etc. of data all comply with the relevant regulations 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, processing, etc. of user information have obtained the authorization and consent of the customers.

[0258] It should be noted that the information collected in this application is information and data authorized by the user or fully authorized by all parties. And the processing of relevant data such as collection, storage, use, processing, transmission, provision, disclosure, and application complies with the relevant laws, regulations, and standards of relevant countries and regions, takes necessary confidentiality measures, does not violate public order and good customs, and provides corresponding operation entrances for users to choose to authorize or refuse.

[0259] It should be noted that the technical solution provided in this application provides corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, it enters the expert decision-making process.

[0260] In the technical solution of the general document data conversion method provided by the embodiments of the present invention, through the large model business process processor and the intelligent agent, the business scenario of the obtained user input text is analyzed and the rule fields are extracted to generate a recommended rule template; through the large model business process processor, according to the adjustment requirement text input by the user, the configuration fields of the recommended rule template are updated to generate a target document conversion rule template; according to the target document conversion rule template, the source document data is subjected to general data mapping conversion to generate the document data model of the target document. By configuring the document conversion rule template, dynamic code-free automation configuration is realized, the reusability is improved, and the automatic conversion of homogeneous data and heterogeneous data to the general document model can be satisfied in complex scenarios, shortening the delivery cycle and reducing the delivery cost; the multiple write-off relationships can be recorded according to the write-off relationship table, any revocation mechanism is supported, the document redundancy is reduced, and the flexibility of write-off relationship processing in document conversion is improved.

[0261] Figure 5 FIG. is a schematic structural diagram of a general document data conversion device provided by an embodiment of the present invention. The device is used to execute the above general document data conversion method, as Figure 5 shown. The device includes: a recommended rule template generation unit 11, a target document conversion rule template generation unit 12, and a general data conversion unit 13.

[0262] The recommended rule template generation unit 11 is used to analyze the business scenario of the obtained user input text and extract the rule fields through the large model business process processor and the intelligent agent to generate a recommended rule template.

[0263] The target document conversion rule template generation 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 process processor to generate a 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 the document data model of the target document.

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

[0266] In the embodiment of the present invention, the target document conversion rule template generation unit 12 is specifically configured to, through the large model business process processor, identify the adjustment content of the adjustment requirement text, and 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 correspond 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.

[0269] In the embodiment of the present invention, a first template determination 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 an 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 trigger unit 17.

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

[0273] The trigger unit 17 is used to trigger the automatic order generation operation if the condition is 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 configured to perform format conversion and standard encapsulation on the heterogeneous data through the set document conversion adaptation facade, or perform standard encapsulation on the homogeneous data to generate the standardized source document data; perform field mapping conversion on the standardized source document data according to the field rule settings and reference types to generate the target table field data; perform dimensional processing on the target table field data according to the parameter settings to generate the document data model of the target document.

[0275] In an 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 generation unit 18.

[0276] The write-off relationship generation unit 18 is used to generate write-off relationship records according to the data model of the write-off relationship table, based on 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 reverse writing settings; the basic information further includes write-off control numbers; the device further includes: a monitoring unit 19, a verification unit 20, an update unit 21, and a reverse writing unit 22.

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

[0279] The verification unit 20 is used to verify the write-off relationship records according to the write-off control numbers if a save event is monitored.

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

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

[0282] In an embodiment of the present invention, the device further includes: a second template determination unit 23, a rollback unit 24, and a release unit 25.

[0283] The second template determination unit 23 is used to determine the 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 rollback write-back process on the source document data according to the write-back settings and cancellation relationship records in the determined document conversion rule 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 cancellation values in the cancellation relationship records.

[0286] In the solution of the embodiment of the present invention, through the large model business flow processor and the intelligent agent, the business scenario of the acquired user input text is parsed and the rule fields are extracted to generate a recommended rule template; through the intelligent agent, the recommended rule template is updated according to the configuration fields input by the user to generate a target document conversion rule template; according to the target document conversion rule template, the general data mapping conversion is performed on the source document data to generate the document data model of the target document. The dynamic code-free automation configuration is realized by configuring the document conversion rule template, which improves the reusability and can meet the automatic conversion of homogeneous and heterogeneous data to the general document model under complex scenarios, shortens the delivery cycle and reduces the delivery cost; it can record multiple cancellation relationships according to the cancellation relationship table, support any cancellation mechanism, reduce the document redundancy, and improve the flexibility of the cancellation relationship processing in document conversion.

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

[0288] The embodiment of the present invention provides a computer device, including a memory and a processor. 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 above embodiments of the general document data conversion method are implemented. For specific descriptions, reference can be made to the above embodiments of the general document data conversion method.

[0289] Next, refer to Figure 6 , which shows a schematic structural diagram of a computer device 600 suitable for implementing the embodiments of the present application.

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

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

[0292] Specifically, according to an embodiment of the present invention, the processes described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product that includes a computer program tangibly embodied on a machine-readable medium, the computer program including program code for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via communication section 609, and / or installed from removable medium 611.

[0293] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media and can implement information storage by any method or technology. The 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 memory (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 cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information accessible by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0294] For convenience of description, when describing the above device, it is divided into various units according to functions for separate description. Of course, when implementing the present 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 the 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 flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0296] These computer program instructions can 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, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device that implements the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0297] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one process or multiple processes and / or blocks. Figure 1 one process or multiple processes and / or blocks Figure 1 steps for implementing the functions specified in one block or multiple blocks.

[0298] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the said element.

[0299] In the technical solution of this application, the acquisition, storage, use, processing, etc. of data all comply with the relevant provisions of national laws and regulations.

[0300] It should be noted that in the embodiments of this application, some industry-existing solutions such as certain software, components, models, etc. may be mentioned. They should be regarded as exemplary. The purpose is only to illustrate the feasibility in the implementation of the technical solution of this application, but it does not mean that the applicant has already or necessarily used this solution.

[0301] Those skilled in the art should understand that the embodiments of this application can be provided as a method, a system or a computer program product. Therefore, this application can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0302] This application can 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. This application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0303] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and reference can be made to the corresponding part of the method embodiment for the relevant content.

[0304] The above are only the embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various modifications and changes can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A general method for converting document data, characterized in that, The method includes: Parsing the business scenario and extracting rule fields from the obtained user input text through a large model business process processor and an agent to generate a recommendation rule template; Updating the configuration fields of the recommendation rule template according to the adjustment requirement text input by the user through the large model business process processor to generate a target document conversion rule template; Performing 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.

2. The general conversion method for document data according to claim 1, wherein The user input text is a multi-round conversation text, and the multi-round conversation text includes intention description conversation text and information collection conversation text; The step of parsing the business scenario and extracting rule fields from the obtained user input text through a large model business process processor and an agent to generate a recommendation rule template includes: Performing intention recognition on the intention description conversation text through the large model business process processor to generate an order creation type, source document information, and target document information; Performing scenario parsing on the information collection conversation text through the large model business process processor to generate a corresponding business scenario; The agent extracts the source document definition, target document definition, and rule template configuration attributes respectively through the document metadata interface and the document conversion metadata interface according to the order creation type, source document information, and target document information; The large model business process processor matches the business scenario, source document definition, and target document definition according to the rule template configuration attributes to generate an initial rule template; The large model business process processor supplements the fields of the initial rule template according to a preset rule template knowledge base to generate the recommendation rule template.

3. The general conversion method for document data according to claim 1, characterized in that The step of updating the configuration fields of the recommendation rule template according to the adjustment requirement text input by the user through the large model business process processor to generate a target document conversion rule template includes: The large model business process processor identifies the adjustment content of the adjustment requirement text, and the adjustment content includes adjustment fields and corresponding field values; Matching the adjustment fields with the configuration fields of the recommendation rule template to determine the configuration fields to be adjusted; Updating the configuration fields to be adjusted according to the field values to generate the target document conversion rule template.

4. The general conversion method for document data according to claim 1, characterized in that, The method further includes: Setting a document conversion rule template identifier for each target document conversion rule template and associating 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.

5. The general conversion method for document data according to claim 4, characterized in that, The method further includes: In response to the automatic order creation operation triggered by the scheduled task, determining the target document conversion rule template according to the document conversion rule template identifier corresponding to the business scenario of the scheduled task, and the business scenario corresponds to an order creation type, and the order creation type is pull generation or push generation.

6. The general conversion method for document data according to claim 5, wherein The method further includes: Judging whether the document date of the source document data and the current time conform to the automatic order creation setting of the scheduled task; If it conforms, trigger the automatic order creation operation; If not, continue to execute the judgment on whether the document date of the source document data and the current time meet the automatic document generation setting of the scheduled task.

7. The general conversion method for document data 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 general data mapping conversion of 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 set document conversion adaptation facade, perform format conversion and standard encapsulation on the heterogeneous data, or perform standard encapsulation on the homogeneous data to generate the 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, perform dimensional processing on the target table field data to generate the document data model of the target document.

8. The general conversion method for document data according to claim 7, wherein, The target document conversion rule further includes basic information, and the basic information includes a write-off relationship table; After performing dimensional processing on the target table field data according to the parameter settings to generate the document data model of the target document, it further includes: According to the data model of the write-off relationship table, generate a write-off relationship record based on the standardized source document data and the document data model of the target document.

9. The general conversion method for document data according to claim 8, characterized in that, The target document conversion rule further includes reverse write settings; the basic information further includes write-off control numbers; After generating the write-off relationship record according to the data model of the write-off relationship table based on the standardized source document data and the document data model of the target document, it further includes: Through the set document conversion event processor, perform event monitoring on the document model of the target document; If a save event is monitored, verify the write-off relationship record according to the write-off control number; If the verification passes, update the write-off relationship record to the write-off relationship table; Through the set document conversion reverse write processor, according to the reverse write settings, perform reverse write on the source document data according to the write-off relationship record.

10. The general conversion method for document data according to claim 9, characterized in that, The method further includes: If a delete event is monitored, determine the document conversion rule template corresponding to the document model of the target document; Through the set document conversion reverse write processor, according to the reverse write settings and write-off relationship record in the determined document conversion rule, perform reverse write rollback processing on the source document data; Delete the document data of the target document and release the write-off value in the write-off relationship record.

11. A general conversion device for document data, characterized in that The device includes: A recommended rule template generation unit, configured to perform business scenario analysis and rule field extraction on the obtained user input text through a large model business flow processor and an intelligent agent to generate a recommended rule template; A target document conversion rule template generation unit, 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 the document data model of the target document.

12. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the general conversion method for document data described in any one of claims 1 to 10.

13. A computer device, comprising a memory and a processor, the memory being used to store information including program instructions, and the processor being used to control the execution of the program instructions, characterized in that, When the program instructions are loaded and executed by a processor, they implement the general conversion method for document data described in any one of claims 1 to 10.

14. A computer program product comprising computer programs / instructions, characterized in that, When the computer program / instructions are executed by a processor, they implement the general conversion method for document data described in any one of claims 1 to 10.

Images