267 results about "Business documents" patented technology

The invention relates to a dynamic data pipeline construction method based on artificial intelligence and multi-modal data processing, and belongs to the technical field of data fusion treatment and artificial intelligence. According to the method, a multi-modal deep learning model is adopted, semantic analysis is performed on business documents, user requirements and function specification instructions, and key indexes, data requirements and logic constraints are extracted; constructing a multi-modal knowledge graph, performing unified representation and feature extraction on structured and unstructured data resources, and performing embedded learning by using a graph neural network; based on a deep semantic matching model and a hybrid recommendation system, realizing accurate matching of business requirements and data resources; modeling generation of a data processing flow into a Markov decision process by adopting a reinforcement learning strategy, and automatically generating an optimized data processing workflow; the adaptability of the model to new business requirements is improved by utilizing a meta-learning algorithm; and dynamic scheduling and execution of tasks are realized through a workflow engine. According to the invention, the data processing efficiency can be improved.

The invention discloses an AI data warehouse full-link blood relationship tracking method and device, and relates to the technical field of data processing. The method comprises the following steps: obtaining structured log data with business terms and entity tags; establishing a knowledge graph according to the structured log data and the business document; generating blood relationship metadata according to the knowledge graph and the data job execution log; constructing a blood relationship cognition map according to the blood relationship metadata, the data operation log and the business document; generating a governance strategy vector according to the blood relationship cognitive map, the system real-time index and the service SLO, and sending the governance strategy vector to an execution engine, so that the execution engine carries out processing according to the governance strategy vector; and obtaining a governance strategy execution result, user feedback information of the governance strategy execution result and a system log generated in a governance process. According to the method, complex semantics and causal relationships behind data operation can be captured.

Recent developments in machine learning (commonly coined "artificial intelligence" or "AI") have vastly expanded applications for this technology, such as myriad "chat" agents adept at understanding natural human language. While state of the art generative models can parse text queries from a user and provide comprehensive, accurate responses (including generating images depicting desired content), current implementations struggle with understanding all information present in images of documents, especially images of business documents. In particular, generative models fail to understand structured and semi-structured information, e.g., as indicated by graphical information such as lines, geometric relationships (e.g., indicated by tables, graphs, figures, etc.), formatting, and other contextual information that human readers easily and implicitly understand. The disclosed inventive concepts transform structured and semi-structured information along with textual content into a textual representation that allows generative models to better understand textual content and non-textual structured information present in document images.

The invention provides an intelligent business document approval method and approval system based on a large model, and the method comprises the steps: analyzing an unstructured text, and extracting an audit rule for a business document from the unstructured text according to a historical data analysis result and a risk assessment result; the extracted auditing rule is stored based on a comprehensive rule knowledge base, the comprehensive rule knowledge base comprises a recessive rule and an expression description rule, and the auditing rule is updated when the business relation is changed; and automatically examining and approving the obtained business document according to the stored examination and approval rule, generating a cue word by combining the business data in the business document according to a preset examination and approval scene and a general rule, automatically examining and approving the business document based on the cue word and the business data by utilizing a large model, and returning an examination and approval result. The invention further provides an approval system for implementing the method. When the business document is approved, the requirement of the implicit rule for the approval is considered, and the approval quality is improved.

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 embodiment of the invention provides an information extraction method and a field selection method, and the information extraction method comprises the steps: displaying a field selection page containing a business sample document according to business query information, and determining a query field corresponding to the business query information; in response to a selection instruction submitted through the field selection page, determining a selection field having an association relationship with the query field in the business sample document; recalling a candidate document paragraph set in a business document library according to the query field, and inputting the query field and the selection field into a large language model; and recalling a target document paragraph in the candidate document paragraph set through the large language model, and extracting target information associated with the business query information in the target document paragraph by using the large language model according to the selected field. The information extraction operation is driven in a user-defined field selection mode, so that the information extraction precision is effectively improved.

Recent developments in machine learning (commonly coined “artificial intelligence” or “AI”) have vastly expanded applications for this technology, such as myriad “chat” agents adept at understanding natural human language. While state of the art generative models can parse text queries from a user and provide comprehensive, accurate responses (including generating images depicting desired content), current implementations struggle with understanding all information present in images of documents, especially images of business documents. In particular, generative models fail to understand structured and semi-structured information, e.g., as indicated by graphical information such as lines, geometric relationships (e.g., indicated by tables, graphs, figures, etc.), formatting, and other contextual information that human readers easily and implicitly understand. The disclosed inventive concepts transform structured and semi-structured information along with textual content into a textual representation that allows generative models to better understand textual content and non-textual structured information present in document images.

Recent developments in machine learning (commonly coined “artificial intelligence” or “AI”) have vastly expanded applications for this technology, such as myriad “chat” agents adept at understanding natural human language. While state of the art generative models can parse text queries from a user and provide comprehensive, accurate responses (including generating images depicting desired content), current implementations struggle with understanding all information present in images of documents, especially images of business documents. In particular, generative models fail to understand structured and semi-structured information, e.g., as indicated by graphical information such as lines, geometric relationships (e.g., indicated by tables, graphs, figures, etc.), formatting, and other contextual information that human readers easily and implicitly understand. The disclosed inventive concepts transform structured and semi-structured information along with textual content into a textual representation that allows generative models to better understand textual content and non-textual structured information present in document images.

The invention provides an evaluation method of data elements in a model application, related hardware and a program product. The method comprises the following steps: acquiring metadata knowledge and content knowledge of target data elements from a metadata knowledge base and a content knowledge base set by a big language model hitching data platform, and storing the target data elements in the data platform. Setting the metadata knowledge and the content knowledge of the target data element as cue words to be imported into a large language model so as to execute the following steps through the large language model: generating a query language order based on the metadata knowledge of the target business document, and querying a data platform according to the query language order to obtain a query result; and determining a matching degree between the query result and the content knowledge of the target data element. And based on the matching degree between the query result and the content knowledge of the target data element and the cost of applying the target data element to the large language model, determining the efficiency of applying the target data element to the large language model.

The embodiment of the invention discloses a data query method based on a natural language, related equipment and a storage medium, and is used for the field of language processing. In the method, based on a business scene to which a natural language statement belongs, a target business document corresponding to the natural language statement is positioned, and a target business field in the natural language statement is split; recalling field metadata of the target business field from a document knowledge base corresponding to the target business document; generating a database statement based on the field metadata of the target business field; the field metadata recalled from the receipt knowledge base is the field metadata of the business fields of the same business receipt in the business scene, mutual interference of the metadata is effectively avoided during receipt knowledge base recall, the accuracy of receipt knowledge base recall is improved, the accuracy of database statements is improved, and the accuracy of data query is improved. The method can be applied to various business systems, such as an enterprise resource planning (ERP) system, an enterprise management system, a manpower system and the like.

The embodiment of the invention provides a power business document processing method and device, equipment, a computer storage medium and a computer program product. The method comprises the following steps: acquiring an unstructured document corresponding to an electric power business hall service system; identifying basic content blocks contained in the unstructured document based on a preset document structure rule; based on the complexity of each basic content block, determining a target server to which each basic content block is allocated from a server cluster; extracting key service information in the corresponding basic content block through the target server; and fusing the key business information into a power business knowledge graph corresponding to the power business hall service system to obtain a power business document database. According to the method, the structured processing efficiency of the power business document and the management efficiency of the power business information in the power business hall are improved.

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 invention discloses a financial business document verification method and device, equipment and a medium, and relates to the technical field of computers, and the method comprises the steps: obtaining a verification request of a current business document, and reading the text content in the current business document to obtain a formattless text document; the current business document is a document obtained by filling an initial data table stored by a business system based on business data; determining a target rule verification template from a template library according to the verification request; performing field extraction operation on the text document and the to-be-verified business table based on the target rule verification template to obtain a corresponding filling value and an actual business value; the to-be-verified business table is a latest data table stored by the business system based on the business data corresponding to the approved data; and performing comparison verification on the filling value and the actual business value to obtain a business verification result. Therefore, the accuracy of data extraction can be improved, and the accuracy of checking the data in the to-be-checked business table and the data in the business document stored in the business system is improved.

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 provides a large model privatization deployment scheme evaluation method and device, and the method comprises the steps: pre-determining a target problem and a target business document for a to-be-tested large model, and obtaining an insurance capability score of the to-be-tested large model based on the target problem and the target business document; deploying the to-be-tested large model on preset to-be-tested hardware, inputting the target problem into the to-be-tested large model to obtain multi-dimensional performance index data when the to-be-tested large model works on the to-be-tested hardware, and obtaining a hardware performance test score of the to-be-tested large model based on the performance index data; and testing the multi-dimensional reasoning ability of the to-be-tested large models to obtain reasoning ability scores of the to-be-tested large models, and obtaining deployment scores of the to-be-tested large models when the to-be-tested large models are deployed on the to-be-tested hardware platforms based on the reasoning ability scores, the insurance ability scores and the hardware performance test scores.

The invention provides a network-based service document multi-person cooperation message triggering type synchronization method and system, and relates to the technical field of computer networks, and the method comprises the steps: S1, employing a condition triggering type point-to-point lightweight message synchronization method from Client to Server to Client; s2, establishing a WebSocket communication connection between the client side and the server; s3, interactive transmission of data is carried out through a TCP protocol, the structure of a protocol packet comprises a Header part and a Body part, and the Header part is composed of a client MAC address of a Client, a login user identifier and a timestamp; the Body part is composed of a command identifier and a document number; and S4, generating a unique document identifier ERI for each document. According to the method, the situations that the collaboration efficiency of business receipts is low, errors are prone to occurring, and data are inconsistent can be avoided.

To provide a system.SOLUTION: The system includes: means for automatically generating a business document from an instruction; means for checking a grammatical error in the generated business document; means for checking compliance of the generated business document; means for determining whether the generated business document conforms to the standard of a business communication; analyzing the generated business document by using a natural language processing technology; and means for repairing the business document on the basis of the result of analysis.SELECTED DRAWING: Figure 1

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 relates to the technical field of data retrieval, and discloses a watershed business document approximate search method, device and equipment and a medium, and the method comprises the following steps: obtaining a watershed business knowledge document, and carrying out dimension reduction compression coding on the watershed business knowledge document to obtain a contrast value function; performing empirical mode decomposition on the contrast value function to obtain a plurality of intrinsic mode function components, and integrating the plurality of intrinsic mode function components in the same coordinate system; clustering the drainage basin business knowledge documents corresponding to the same intrinsic mode function component to obtain a plurality of clustered documents; obtaining a query document, respectively calculating mahalanobis distances between query points corresponding to the query document and the plurality of intrinsic mode function components, and selecting a clustering document as an approximate document based on the mahalanobis distances; according to the method, the document search efficiency and the response efficiency of watershed knowledge sharing are remarkably improved.

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 relates to the technical field of data processing, and provides a dynamic rule-based automatic voucher generation method and system for business receipts, and the method comprises the steps: obtaining a plurality of historical business receipts, extracting business receipt elements for each historical business receipt, and marking voucher elements; based on the business document elements and the voucher elements of the plurality of historical business documents, generating association rules of the voucher elements and the business document elements through a large language model in combination with the policy data; for each historical business document, calling association rules related to business document elements of the historical business document, and storing the association rules; and obtaining a to-be-processed business document, extracting business document elements, searching for the historical business document with the highest similarity, and generating voucher elements through the association rule stored in the historical business document with the highest similarity. And a new scene can be covered without manually modifying the template, so that the dependence on a static rule is eliminated.

The invention relates to the technical field of data processing, in particular to a large-scale business document data rapid clustering retrieval method, which comprises the following steps of: obtaining a target retrieval word of a current retrieval person; acquiring browsing duration of historical retrieval words and documents corresponding to each historical retrieval record under each gradient level; determining a retrieval matching degree, a browsing confidence degree and a retrieval association degree of each document in the retrieval library of any level; obtaining a retrieval related class, a retrieval unrelated class and a reference related class; determining false positive possibility and false negative possibility; determining a false positive document in the retrieval related class and a false negative document in the retrieval unrelated class; and adding and deleting the false positive document and the false negative document to obtain an adjusted retrieval related class, and displaying a retrieval result of the target retrieval word of the current retrieval person. According to the method and the device, the document clustering accuracy can be improved, the document retrieval speed and efficiency are improved, and the document retrieval result is more accurate.

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 discloses an anomaly analysis method and device for production management and electronic equipment, and relates to the field of data processing. The method comprises the following steps: acquiring a plurality of production orders, and generating a corresponding process tracking code for each production order; associating the process tracking code to a business document in a production management system to generate an associated data set; based on the associated data set, constructing a multi-dimensional production element map, and based on the multi-dimensional production element map, generating a three-dimensional process sand table, the three-dimensional process sand table comprising a topology view, a thermodynamic view and a tracing view; inputting the process delay event into the three-dimensional process sand table, determining upstream and downstream nodes and edges related to the process delay event, and forming an abnormal propagation path; and based on the abnormal propagation path, reasoning the process delay event to obtain an abnormal reason. By implementing the technical scheme provided by the invention, the abnormal reason is quickly positioned, and the production efficiency is improved.

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 a training method and device of a document compliance detection model, equipment and a medium, and relates to the technical field of data processing.The method comprises the steps that a sample business document, a labeling result of the sample business document and set rule configuration information are obtained; the sample business document comprises a sample business text and a sample business chart; extracting a to-be-detected text entity from the sample business text through the initial detection model, and identifying a to-be-detected data item from the sample business chart; according to the to-be-detected text entity, the labeled text entity, the to-be-detected data item, the labeled data item and set rule configuration information, performing compliance detection on the sample business document to obtain a compliance detection result; and according to the compliance detection result, the labeling result and the sample business document, training the initial detection model to obtain a document detection model. According to the method and the device, the efficiency and the accuracy of compliance detection on the business document are improved.