123 results about "Business documents" patented technology

The invention relates to the field of discrete manufacturing intelligence, in particular to an intelligent decision-making and business collaboration method based on an OAG ontology and an LLM large model, which comprises the following steps: collecting historical data and business documents, and performing directional fine tuning on a basic large language model to form the LLM large model; the method comprises the following steps: analyzing discrete manufacturing scene original data and business documents, and constructing an OAG ontology library; receiving field data in real time through the LLM large model, updating the OAG ontology library, and performing feedback optimization on the LLM large model to form bidirectional feedback; integrating real-time data and historical data, inputting the data into an LLM large model, converting the data into business knowledge through layering of an OAG ontology library, and generating a main and standby decision scheme; and establishing an agent federated center, issuing a decision scheme, collecting execution data and feeding back an LLM large model, and realizing cross-scene collaboration and full-process data closed loop. According to the invention, through a technical path of a whole-process data closed loop, a core pain point that an existing LLM does not understand a business is effectively solved, and whole-link value conversion of discrete manufacturing data is realized.

The invention discloses a business document design and user-defined field modeling method supporting dynamic expansion. The method relates to the technical field of custom field modeling, and comprises the following steps: constructing a core foundation and a metadata system; a non-intrusive expansion and data association model; performing high-performance query and index optimization; and performing dynamic verification and visual application. Structural stability and flexible expansion are realized through separate design of the core table and the expansion table, field definition, storage, verification and form rendering are driven by metadata, complex query and cross-receipt field multiplexing are supported, data consistency and full-link connection are guaranteed, business receipt design and self-defined field modeling expandability are improved, and the method is suitable for large-scale popularization and application. The problem of low expandability of business document design and custom field modeling in the prior art is solved.

The embodiment of the invention discloses a business receipt and invoice data matching method and system, and the method comprises the following steps: accessing original business receipt data and invoice data from a plurality of heterogeneous data sources through a uniform interface, and carrying out the data cleaning according to preset mapping, merging, splitting and conversion rules, generating a standardized matching flow order; adopting streaming data loading and a Worker parallel computing mechanism to carry out multi-dimensional matching on business receipt and invoice data in the standardized flow bill, and generating a relation matrix representing a corresponding relation between the receipt and the invoice based on a matching result; and automatically checking the relation matrix by calling a rule engine and a machine learning model, marking the matching result of the business document and the invoice which are checked to be abnormal, pushing the matching result to manual auditing, and feeding back the manual auditing result to a knowledge base to optimize the subsequent matching and checking rule. According to the embodiment of the invention, the matching efficiency of the business document and the invoice data and the accuracy of the matching result can be improved.

The invention discloses a food business review method and device based on an intelligent agent, equipment and a storage medium, and relates to the technical field of large models, and the method comprises the steps: receiving a to-be-reviewed food business document through a scheme generation intelligent agent, calling a food field review agent, matching a template matching instruction issued by the scheme generation agent with the first cue word template library, and determining a target rule retrieval tool; performing secondary matching in a second cue word template library by utilizing a target rule retrieval tool and a template matching instruction issued by a food field review agent, obtaining an initial retrieval result from a preset rule database, and performing supplementary retrieval to obtain a final target retrieval result if the initial retrieval result does not meet a matching condition; and comprehensively analyzing the target retrieval result and the first template matching result by the food field review agent, generating a compliance judgment result, returning the compliance judgment result to the scheme generation agent, and outputting a business review result and a solution according to the compliance judgment result. Therefore, the efficiency of reviewing the document can be improved.

The invention relates to the technical field of business and financial general voucher conversion, and provides a general method for visually converting a business document into a financial voucher, which comprises the following steps of: S1, defining a business data structure table, extracting business data from a business system and storing the business data in the table; s2, maintaining subjects, auxiliary accounting basic data and a voucher template, and establishing an association matching relationship between service auxiliary accounting and financial auxiliary accounting; s3, establishing an entry generation rule, maintaining basic generation setting, setting source business data, and configuring an entry detail processing rule; s4, processing and generating standard entry data based on the data in the business data structure table and entry generation rules, and verifying and auditing the standard entry data; and S5, establishing a rule of converting the entry data into the voucher data according to the format requirement of the target financial system, and converting the standard entry data into the voucher data conforming to the format of the financial system. The problems of knowledge reuse, personnel requirements, communication cost, system suitability and the like of a traditional scheme are solved.

The invention provides a service logic vulnerability detection method and device, equipment, a medium and a program product, and relates to the technical field of network security. The method comprises the following steps: constructing a business process state machine through a key entity obtained by performing natural language analysis on a business document; the business process state machine is used for describing state changes of the business process in different stages; obtaining an operation sequence generated based on the interaction operation through a flow agent deployed in a network environment; carrying out modeling and feature extraction on the operation sequence based on a hierarchical attention circulation network to obtain operation behavior features; comparing the operation behavior characteristics with a business process state machine to obtain a vulnerability detection result; the vulnerability detection result comprises permission violation and / or flow abnormality.

The invention discloses a general data exchange system based on a configurable label structure, which relates to the technical field of data processing and information integration, and comprises a parameter module used for establishing an identity authentication mechanism of two exchange parties; the business document module is used for establishing a data structure definition based on a preset exchange demand; the receipt logic module is used for carrying out logic analysis and code decoupling on the data structure definition, generating a marked language script code and an execution instruction, constructing an execution matrix and realizing mapping between a database physical field and a memory logic variable; and the standard adaptation module is used for comparing and checking the content of the generated data and feeding back a checking result to the parameter module to correct the exchange rule and parameter configuration. A more intelligent logic separation strategy is implemented through structural insight, data reading, writing and transmission are cooperatively controlled, complete decoupling of service logic and program codes is achieved through a nested tag structure, and flexibility, universality and maintenance efficiency of data exchange are optimized.

The invention provides a multi-source bill processing method and device, electronic equipment and a medium, and relates to the technical field of computer software, and the method comprises the steps: carrying out the preprocessing of obtained bill data, and obtaining target bill image data; inputting the target bill image data into a multi-modal model for feature extraction to obtain structured text information, visual layout information and semantic association information of the bill data; based on the structured text information, the visual layout information and the semantic association information, whether repeated bills exist or not is determined; when it is determined that no repeated bills exist, compliance verification is carried out on the bill data, and a compliance verification result is obtained; processing the bill data of which the compliance verification result is passed and the configured business bill to obtain a bill knowledge graph; and carrying out cost collection processing on the bill data corresponding to the bill knowledge graph to generate accounting document data. The method can greatly improve the bill processing efficiency, and guarantees the credibility and traceability of the whole process of the bill.

The invention discloses an intelligent process approval method and device based on a dynamic rule engine and a medium, and relates to the technical field of informatization management, and the method comprises the steps: obtaining a business document of an initial approval scene, and obtaining an initial approval data model through scene field configuration based on the business document of the initial approval scene; according to the initial approval data model, determining an initial approval process through an approval process definition of node configuration; performing self-evolution analysis of a dynamic rule engine on the initial approval process to obtain an updated dynamic rule engine; obtaining submission approval, and performing process node approval instantiation on the submission approval based on the updated dynamic rule engine to determine approval instance information; and based on the approval instance information, obtaining subsequent approval nodes through state analysis of the approval nodes. Through the method, the technical problem that the rule type and the approval node cannot be automatically updated in the existing process approval technology is solved.

The invention discloses an electronic archive management method for a business document generation layout file, and belongs to the technical field of electronic archive management. Comprising the following steps: constructing a multi-dimensional feature vector by collecting business document scene features, screening candidate templates from a template pool by adopting a multi-level similarity matching algorithm, and adjusting and determining a target template in combination with a dynamic structure; the basic metadata and the associated system data are integrated, and qualified metadata is output through multi-level rule verification and abnormal data correction; based on the target template, executing data filling typesetting and format resource preprocessing by adopting a double-thread asynchronous processing mechanism, and generating a layout file conforming to PDF / OFD double standards through an adaptive algorithm; calculating a hash value of the layout file and writing the hash value into a block chain to realize tamper-proof evidence storage, and realizing secure storage and quick retrieval by adopting a distributed architecture in which a main file is separated from an index file. According to the method, the problems of low template matching precision, incomplete data verification, low processing efficiency, insufficient file safety guarantee and the like in the prior art are solved.

The invention relates to an intelligent allocation method for combined settlement funds. The method comprises the following steps: collecting key data from various business receipts and storing the key data; extracting the sorted key data, and judging a specific business scene to which the business belongs; according to the business scene, calling a corresponding fund allocation priority algorithm, and calculating a settlement amount, a settled amount, an unsettled amount and a verification amount of each business document; and feeding back a calculation result to a business document system and a financial system, and updating amount data of related documents. According to the invention, dynamic adjustment can be carried out according to the characteristics, the time sequence and the amount weight of the business document, so that the rationality and accuracy of fund allocation are ensured; the allocation efficiency is improved, and the complexity and the error rate of manual operation are reduced, so that the fund flow management is optimized; the flexibility and adaptability of the system are enhanced, and individual requirements of enterprises in different business scenes can be better met.

The invention discloses an intelligent customer service knowledge base automatic updating method based on a large language model, and relates to the technical field of knowledge base management, and the method comprises the steps: collecting a multi-source business document and session data, cleaning and merging the multi-source business document and the session data, calling the large language model to extract candidate entries, and binding evidence fingerprints; performing consistency comparison and change type judgment on the candidate entries and knowledge base entries, and generating and solidifying a difference abstract; generating a semantic patch according to the difference abstract, writing the semantic patch into a shadow partition, completing consistency verification, enabling atomic switching to take effect, synchronously updating a reverse index view and a vector index view of the intelligent customer service knowledge base, and recording a version mark; and performing online verification on a session data statistical result according to the version mark, rolling back to a state before the version mark when the verification result is abnormal, and confirming the semantic patch and continuously acting on the intelligent customer service knowledge base when the verification result is normal. The release risk is reduced; and the knowledge reliability and auditing performance are improved.

The invention relates to the technical field of computers, in particular to an intelligent approval method and system based on detail line multi-dimensional attributes. The method comprises the following steps: receiving a business document containing a plurality of detail lines, and preprocessing data in the detail lines to obtain standardized detail data; for any standardized detail data, extracting multi-dimensional key business attributes, and selecting an approval flow from a preset approval flow set in combination with each key business attribute; and each detail line examines and approves each standardized detail data along the respective examination and approval process, and performs a downstream business process according to the examination and approval result. The method has the effect of improving the business process processing efficiency.

The application relates to a business document information extraction method based on variant attention and hierarchy, and belongs to the field of natural language processing. First, the document is classified, the data is processed into supervised training data required by a model, and is input into a variant attention and hierarchy network model for training, and a hierarchical network structure is used to extract features of word-level, sentence-level and paragraph-level document information; the document required to be extracted and the label of the content of the document required to be extracted are input into the trained hierarchical variant attention network model for information extraction; and finally, the extracted information is statistically analyzed. The application realizes accurate business document information extraction technology, and finally, the document information is extracted through the technology, and then the document information is statistically analyzed to realize special business related information extraction.

This invention discloses a method and system for detecting confidential business documents based on sensitive subgraph matching in a cold start scenario, belonging to the field of information detection technology. The method includes: acquiring a set of short text confidential business documents; constructing a global knowledge graph based on the set of short text confidential business documents, and extracting confidential business patterns from the global knowledge graph through subgraph matching; reorganizing the confidential business patterns into logically coherent long text; training a discriminator based on the long text, and generating confidential business detection results for the target document based on the trained discriminator. This invention can quickly achieve usable detection performance under cold start conditions, explicitly model the structured features of confidential business information, and support a dynamic balance between efficiency and effectiveness in real-time scenarios, thereby improving the credibility and practicality of the confidential business detection system in actual enterprise deployments.

The invention relates to an extensible aid decision-making method and system based on cross-border trade management, and belongs to the technical field of computer information processing. The method comprises the following steps: acquiring a cross-border trade auditing workflow map to bind an auxiliary decision-making unit, and when a business document is triggered, sending a business node decision-making request to the auxiliary decision-making unit according to packaged business data; constructing a multi-strategy auditing fusion model, obtaining an auxiliary decision-making unit list bound with the nodes, concurrently returning decision-making sub-results based on an asynchronous scheduling mechanism, and outputting a structured auditing evidence report; driving an auditing decision process according to a pre-configured branch routing rule, and when entering a manual auditing path, pushing the structured auditing evidence report as a task attachment to a manual auditor through a message array to generate decision feedback data; and regularly starting an optimization task to retrieve decision misjudgment cases in the review knowledge base, and updating the multi-strategy review fusion model.

The invention relates to the technical field of testing, and discloses a test case generation method and device, equipment, a medium and a program product. The method comprises the following steps: acquiring a business demand document and business scene information; according to business demand information and business scene information in the business demand document, multi-path recall is carried out in a knowledge base, recall results are reordered, a knowledge graph for indicating business entities, historical test cases, historical business documents and association relationships among the business entities, the historical test cases and the historical business documents is stored in the knowledge base, and the business entities carry attribute information; the attribute information comprises a marked test point corresponding to the service entity and a label for indicating a service scene corresponding to the marked test point; generating an enhanced context according to a reordering result and the business demand information; according to the enhanced context, generating a test point corresponding to the business demand document; and generating a corresponding test case according to each test point corresponding to the business demand document. And the accuracy of the test case and the comprehensiveness of coverage are improved.

The invention relates to a business document identification model training method and device, equipment and a storage medium. The method comprises the steps of obtaining a historical business document image of a target business, extracting original business data in the historical business document image, and constructing an original text library of the target business; determining a standard term library of the target business, and aligning terms in the original text library with terms in the standard term library to obtain a standardized entity dictionary of the original text library; based on the data format difference of the term fields between the standard term library and the standardized entity dictionary, updating the standardized entity dictionary to obtain a key information parent library; constructing a model training sample based on the standardized entity dictionary, the key information maternal library and respective occurrence frequencies of term fields included in the key information maternal library; the business document recognition model is obtained through training of the model training sample, and the accuracy of recognition of the business data in the business document image of the target business can be improved.

The application provides an engineering digital work order data automatic auditing method and system, relates to the technical field of data processing, and comprises the following steps: configuring a business auditing rule for an engineering digital work order which is structured and split, and generating a business rule account through an aggregation mechanism; extracting an atomized identification item and an atomized mapping item in the business rule account, and respectively associating the atomized identification items with the input parameters of a conditional topology structure to construct a system rule; combining the atomized mapping items to configure a data verification rule for the system rule, determining a rule execution path and a rule trace path of the system rule according to the data verification rule; determining an abnormal business document according to the business rule account by calling the rule execution path, and determining an abnormal atomized identification item corresponding to the abnormal business document according to the rule trace path. The application realizes automatic auditing and accurate positioning of complex work order data, and improves the accuracy and efficiency of engineering auditing.

This invention discloses a real-time assessment method for in-transit inventory costs based on process-oriented tracking and statistics, belonging to the field of logistics cost accounting technology. It aims to solve problems such as lagging in-transit inventory cost accounting, reliance on manual labor, inability to dynamically calculate, and difficulties in full-chain traceability. This invention constitutes a complete solution through layered creation of tracking pools, automatic aggregation based on logistics identifiers, real-time rolling calculation triggered by events, and full-chain aggregation presentation centered on contract numbers. On the one hand, it achieves real-time, automatic, and accurate accounting of in-transit inventory costs through automatic aggregation and rolling calculation of costs throughout the entire process from order to warehousing. On the other hand, through dynamic updates and deep traceability, as well as strengthening the correlation query between contract numbers and accounts payable and business documents, it provides enterprises with unprecedented cost transparency and control capabilities, fundamentally overcoming the core defects of existing technologies.

The application discloses a kind of methods and systems for solving electronic accounting archives attachment file archiving, comprising: determining the type of electronic accounting archives attachment file needing to be archived, determining the acquisition mode according to the type, and obtaining target attachment file needing to be archived based on the acquisition mode;According to the type of target attachment file, the key field for extracting key information is determined, and the key information is extracted from the target attachment file according to the key field, to obtain the first key information;According to the first key information, the matching of business document or accounting voucher is carried out, to obtain the business document or accounting voucher corresponding to the target attachment file;The target attachment file, corresponding business document or accounting voucher is associated, and the archiving of the target attachment file is completed.The present application can improve the efficiency of enterprise file collection, reduce the situation of file loss, reduce the cost of manual participation and file printing related cost.

The invention provides a business document processing method and device, equipment and a storage medium, and the method comprises the steps: obtaining a business document image; the business document image is recognized, business document information corresponding to the business document image is obtained, the business document information is input into a rule verification model, a rule verification result output by the rule verification model is obtained, and the rule verification model comprises a first rule base obtained through a machine learning model in advance; the machine learning model is a model obtained by training with historical business document information as input and business document rules as output in advance, and a processing scheme of the business document is determined based on a rule verification result. According to the method, the business document rule in the historical data can be mined through a machine learning method, and the deep business document rule can be acquired more quickly and accurately, so that the business document can be identified and verified more efficiently and accurately based on the business document rule.

Embodiments of the present application disclose a data processing method and device, computer equipment and a storage medium, comprising: obtaining a first data transmission request for a business collaboration document; the first data transmission request carries a document permission identifier and a transmission connection identifier; the document permission identifier is identifier information determined based on a business object for the document permission of the business collaboration document; the transmission connection identifier refers to identifier information corresponding to a first block transmission channel established for the business object; based on the document permission identifier and the transmission connection identifier, performing permission verification on the business object to obtain a first verification result; when the first verification result indicates that the business object has legal permission, setting a transmission maintenance period for the first data transmission request, and executing a document operation corresponding to the first data transmission request within the transmission maintenance period, generating a business document message associated with the document operation, and returning to the business object. By adopting the embodiments of the present application, resource consumption can be reduced.

The embodiment of the present specification discloses a business file splitting and summarizing method, device and equipment. A business system sends a business file to be processed to a file splitting system, splits the business file into multiple records, and then calls back to the business system. The business system adds a classification identifier to the records according to business logic, and then returns the records to the file splitting system. Thus, the business records can be classified according to the classification identifier, and a summary file can be generated.

The application discloses a kind of based on driving engine's semiconductor manufacturing business document automation management method and system, to solve the problem of low efficiency caused by order whole process manual dependence.The method obtains customer production demand by driving engine, and is automatically converted into customer order, service order and manufacturing order according to preset mapping rule and is issued to manufacturing execution system;Driving engine receives execution result and automatically updates service order and customer order state until closed loop.Driving engine uses exponential backoff retry strategy and task state machine to manage abnormal conditions, support topology dependence analysis of parallel / serial order.The application realizes order whole process automation promotion and real-time monitoring, reduces manual intervention, and improves production efficiency.

The invention relates to a receivable reconciliation method based on hierarchical cancel-after-verification verification, and the method comprises the steps: creating and maintaining a hierarchical verification mechanism which comprises a receipt generation layer verification mechanism; a business process node layer verification mechanism; a financial settlement layer verification mechanism; establishing a verification rule base, and determining and verifying calculation rules of various amounts according to different types of business documents; setting an event-driven model, and realizing automatic verification by calling a verification logic code; and on a front-end interface, obtaining verification result data based on the script, and filling error information into popup window content to be displayed to the user. According to the method, data accuracy is ensured through a layered verification mechanism, and human errors are reduced; the account checking period is shortened by an automatic checking and feedback mechanism, and the working efficiency is improved; the flow continuity is enhanced by optimizing receipt associated information display; and timely and visual verification result feedback facilitates rapid positioning and processing of problems, and the efficiency and accuracy of receivable reconciliation are improved.

The application discloses a public health material classification coding unified management method based on a knowledge graph, and relates to the technical field of public health material management. The method acquires heterogeneous business documents in a public health material supply chain, extracts material original name entities, business flow conversion nodes and packaging specification conversion characteristics, and constructs a context mapping subgraph. The context mapping subgraph is aligned with a public health material standard knowledge graph, a spatial topology connected path is analyzed, a standard material candidate node list is generated, graph structure characteristics are aggregated in combination with multi-order neighbor node characteristics and heterogeneous conflict feature vectors, semantic disambiguation is completed, a target standard node is locked, and a corresponding material standard unified code is output. Further, packaging topology evolution consistency verification is performed on new material name entities in downstream flow documents, and when the verification is consistent, synonymous nodes in the knowledge graph are updated, and when the verification is abnormal, an account-material blocking instruction is output.

The invention discloses a building full life cycle monitoring management system and method, and relates to the technical field of engineering management, and the method comprises the steps: constructing a digital thread topology, building an object passport and an object identifier, and forming a digital thread topology table; when a business document is formed in an engineering business link, uniformly packaging a thread event shell and associating the digital thread topology table to form a thread event flow, and updating object passport information at the same time; and according to the thread event flow, maintaining a full-cycle state record table compiled according to the object identifier, and executing permission check and precondition check to generate an instruction list and a gap exception list. According to the method, the full-cycle state record table is generated through the thread event flow, the ready item field and the event track field are compared and verified, the instruction list or the gap exception list is formed in combination with permission verification and precondition verification, and the certainty and interpretability of process propulsion are achieved.

The invention provides a loan business document auditing method and device, equipment, a storage medium and a product, and relates to the technical field of finance. The method comprises the steps of obtaining text information corresponding to a to-be-audited loan business document, and performing vectorization processing on the text information to obtain text vector information; field vector information corresponding to at least one auditing index is extracted from the text vector information, a preset prompt word template is called according to the field vector information corresponding to each auditing index, and auditing prompt words corresponding to the field vector information are generated; and inputting the field vector information corresponding to the at least one auditing index and the auditing prompt word corresponding to each piece of field vector information into an artificial intelligence auditing model, and generating auditing result information corresponding to the loan business document. The method can improve the auditing efficiency of the loan business document.