25 results about "Rule checking" patented technology

The work ticket intelligent checking method based on multi-modal large model knowledge graph and large model reasoning belongs to the field of power system application technology, first extracts text feature vectors and image feature vectors through an OCR module and an image encoder, forms a comprehensive semantic representation after multi-modal fusion. Extract entities and relationships from power safety regulations and historical operation data to generate a power safety knowledge graph. Check the format and integrity of the basic fields on the ticket, use LLM to combine context and graph nodes for semantic reasoning to generate semantic judgment results. Fuse three layers of results to calculate a comprehensive checking score and output an intelligent determination result. The present application introduces multi-modal input analysis, knowledge graph construction and large model semantic reasoning technology to construct a structured, interpretable and iteratively optimized intelligent work ticket checking system that realizes the full-process intelligentization from ticket image recognition to semantic understanding and from explicit rule checking to implicit logical reasoning.

This application provides a mask rule checking method, system, and terminal based on gradient descent algorithm. It traverses all graphic edges in the chip design layout and filters one or more neighboring edges for each graphic edge. Using a proximity cost function, it calculates the proximity cost value and cost gradient value between each graphic edge and its neighboring edges to calculate the total proximity cost value of the chip design layout, determining whether mask violations exist. If mask violations exist, it calculates the adjustment amount for each graphic edge based on the cost gradient value to update each graphic edge in the chip design layout. By repeating the above operations, iteratively optimizing the position of each graphic edge until no mask violations exist in the chip design layout. Thus, by searching the entire solution space of mask rules, it achieves a globally optimal solution, simultaneously eliminating all mask violations and significantly reducing computational load and saving computational costs.

A mutual correlation foolproof digital medical charging system, S1: information binding and rule presetting: generating a unique identity that can be recognized by an intelligent terminal for each inpatient; S2: point-to-point data acquisition and mutual correlation triggering; S3: mutual correlation foolproof checking: the system receives scanning code information in real time and starts a foolproof engine for checking; S4: intelligent early warning and linkage execution; S5: precise end and review of timed treatment. Advantages: precise matching of consumables and treatment: through rule checking, the misuse and abuse of consumables are prevented, and the compliance and safety of diagnosis and treatment behaviors are ensured.

The application relates to the technical field of unmanned aerial vehicle flight task inspection, and discloses a quick flight task inspection method based on rules and Monte Carlo simulation, which comprises the following steps: analyzing original flight task data, generating structured task data through format analysis and multilevel checking; adopting historical data checking and multidimensional constraint rule inspection to complete safety rule verification; combining model parameter identification and super real-time simulation to output normal working condition simulation report and state point library; generating a simulation working condition set containing initial states and fault configurations based on historical data statistics and importance sampling; obtaining a full working condition simulation result set through adaptive threshold and flight section importance evaluation accelerated simulation; and generating a flight task inspection report through weighted statistics and sensitivity analysis. The application can quickly and comprehensively identify safety risks before task execution, and effectively improves the safety and reliability of flight tasks.

The application discloses a kind of industrial processing based on TVP table value parameter's whole-process digitization management method and system, belong to industrial ERP / MES production management technical field.The application is with TVP table value parameter as core data interaction carrier, realizes the bottom isolation of processing and self-supporting production business by special service mark, adapts the differentiated storage and flexible warehouse management of multiple types of incoming material such as hot rolling, pickling, hard rolling, cold rolling.The centralized storage process is relied on back end, integrates strong transaction control, double rule check, fine post right control, operation full trace, etc., realizes the digitization closed loop of incoming material warehousing, contract binding / cancellation, multi-dimensional query, whole-link tracing, and through TVP drives multi-table linkage synchronization, core data is automatically updated, without manual intervention.The application solves the pain points of traditional system business confusion, non-standard parameter passing, data inconsistency, fuzzy right, tracing difficulty, adopts front-end and back-end decoupling design, can be compatible with existing ERP / MES system seamlessly, has landed stable operation in actual industrial MES system, has mature engineering value and industrialization popularization ability, is suitable for standardization, fine, digitization management of industrial enterprise processing business.The application has been applied completely in actual industrial ERP and MES system, can be long-term stable operation in real production environment, has mature engineering value and industrialization popularization ability.

The application discloses a kind of based on efficient reinforcement fine tuning and rule check multi-modal industrial intelligent detection method and system, method includes: S1.to industrial detection data is divided, and reference sample library and industrial acceptance rule base are constructed;S2.in frozen multi-modal base model, introduce interlayer collaborative adjustment module, and build feature space;S3.in feature space, extract locatable abnormal evidence, and output structured detection result that can be directly accessed in industrial acceptance rule base and check;S4.structurized detection result is input to industrial acceptance rule base and is checked, obtains industrial rule check result;S5.based on industrial rule check result, the related parameter of interlayer collaborative adjustment module is reinforced fine tuning, obtains multi-modal detection model;S6.based on multi-modal detection model, the abnormal detection and industrial acceptance determination of sample to be detected on production line are carried out, obtains final detection result.

The application relates to the technical field of space automatic layout generation and generation process control, and discloses a multi-room consistency layout generation method and system based on generation process constraint modulation. The method comprises the following steps: acquiring space structure information of a target residential space; constructing a multi-room generation state model; constructing and updating a multi-room consistency constraint set in a layout gradual generation process; performing consistency constraint modulation processing on a candidate layout action in a current generation step, so that each room shares a consistency control condition in the generation stage; and outputting a multi-room overall layout scheme satisfying the multi-room consistency constraint set. Compared with the prior art in which each room is independently generated and then subjected to rule checking or scoring screening to realize consistency, the application cooperatively controls consistency relationships such as layout density, furniture scale and space blank proportion in the generation stage, so that the structural rationality, stability and generation efficiency of the multi-room overall layout result are improved.

The present application relates to the technical field of semiconductor manufacturing, in particular to a semiconductor yield analysis optimization method, system, device and medium based on multi-module cooperation; first, a data collection and integration module is used to collect multi-type data of the whole process of semiconductor manufacturing, and cleaning, standardization and integration processing are performed; second, based on the integrated data, a comprehensive yield analysis model is constructed through historical data statistical analysis and physical model simulation, and the key factors affecting yield are located; then, the analysis results and the expected yield are verified through design rule checking, electrical rule checking and yield prediction verification based on the model; finally, based on the verified analysis results, process parameter optimization and design optimization schemes are formulated and executed, and through a feedback iteration mechanism, continuous optimization is carried out to improve yield.

The present application relates to the technical field of integrated circuit mask design, and particularly relates to a mask optimization method and a storage medium, the mask optimization method comprises the following steps: obtaining an initial design graph; performing edge breaking on the initial design graph; obtaining a first distance and a second distance that each broken edge can move based on a mask manufacturing rule and the position of each broken edge; performing mask optimization on the initial design graph, and taking the first distance and the second distance that each broken edge can move as a constraint condition of an optimization algorithm to obtain a target optimization graph. By applying the mask manufacturing rule to the mask optimization, it is ensured that the graph in the optimization process and the target optimization graph meet the mask manufacturing rule requirement, without the need for additional separate mask manufacturing rule checking, greatly improving the efficiency of mask production, and ensuring the yield of the mask. The present application also provides a storage medium.

The application discloses a static aggregation code scene reuse method, a plurality of sets of template application configurations can be configured through an aggregation code, scene coding is transmitted after a code scanning device integrated with an aggregation code SDK scans a code, a business system and a scene are recognized by an aggregation code cli system, and template application configurations adapted to the scene are acquired. After the corresponding template application configurations are read, aggregation code source data is acquired by analysis, and a business execution process is initiated according to the execution type configured. The requested link and parameters can be subjected to rule checking, and the matching of the voucher capability and the scene. A standardized execution process is provided by a unified integrated SDK package, a new business system only needs to be simply integrated and developed to be seamlessly connected into the whole system ecology, the expansibility of the system is enhanced, and meanwhile, the standardized interface integrated mode greatly facilitates the integration of external third-party systems.

A method, device and equipment for auditing operation ticket text and a computer readable storage medium, comprising: inputting a procedure text of an obtained to-be-audited operation ticket text into a first deep learning model to obtain a structured auditing rule output by the first deep learning model; checking the to-be-audited operation ticket according to the structured auditing rule to obtain a rule checking result; inputting the obtained to-be-audited operation ticket text into a second deep learning model to obtain a historical matching result output by the second deep learning model; and generating an auditing conclusion report according to the rule checking result and the historical matching result, thereby solving the technical problems of a traditional auditing system in related technologies, such as dependence on static rules and low data utilization, and achieving the effects of breaking through the limitation of a static rule library and improving data utilization.

The application relates to a power field-oriented multi-modal data automatic labeling method, device, equipment, storage medium and program product. The method comprises the following steps: respectively extracting single-modal features of each data modality in power multi-modal data, and fusing to obtain multi-modal fusion features; calculating the semantic matching degrees of the multi-modal fusion features and each preset label in a pre-constructed domain knowledge base, and determining candidate labels; based on a pre-constructed domain rule base, checking the matching logic between the business attributes contained in the candidate labels and the scenes where the power multi-modal data is located, and obtaining a rule checking result; based on the contents reflected by different data modalities in the power multi-modal data, performing cross-modal consistency comparison on the candidate labels, and obtaining a consistency checking result; and determining a target labeling label of the power multi-modal data according to the rule checking result and the consistency checking result. The method can improve the accuracy of automatic labeling of power business multi-modal data.

This invention belongs to the field of electronic information processing and intelligent bidding technology, and relates to a multimodal bidding technical specification identification method and system. The method includes: acquiring bidding documents and determining their type; preprocessing them into text, scanned documents, and mixed text and image formats to obtain structured data; constructing a label set using industry samples, standards, and historical cases, and training a large model to obtain a knowledge engine containing a parameter library, a clause library, and a risk library; extracting features based on TF-IDF and BERT and matching them with a library to generate classification labels; performing semantic consistency verification and risk rule checking on the results, and correcting them in conjunction with context; mapping the label results to pricing calculation parameters according to association rules and outputting an identification report and a pricing element table. The technical solution of this application forms a closed loop from identification to pricing through unified structured processing, domain semantic recognition, and verification correction, realizing technical specification identification and verification, and improving consistency and traceability.

The application relates to a logistics business rule checking method, a computer device, a storage medium and a product. The method comprises the following steps: generating total checking rules of a logistics business according to checking environment information of the logistics business, wherein the total checking rules comprise multiple rule checking components and rule checking links, and the multiple rule checking components are independent of each other; selecting step: selecting a current rule checking item from all rule checking items of the multiple rule checking components according to the rule checking links; checking to-be-checked business information of the logistics business according to the current rule checking item, obtaining a checking sub-result of a rule checking item of the logistics business; returning to the selecting step under the condition that the current rule checking item is checked, until all rule checking items are selected, and obtaining a checking total result corresponding to all checking sub-results. The method improves the checking efficiency of logistics business rule checking.

This application provides a rule verification method, apparatus, device, and storage medium. The method includes: acquiring preset information of a database table to be verified; then, based on the current polling time interval, performing data verification on the verification fields of the database table where the verification status parameter is a set value; and finally, based on the data verification result and the current polling time interval, determining the latest polling time interval for the database table to be verified. This application solves the problem of low efficiency in verifying rules when they are updated in the prior art, improves the processing efficiency of rule verification, avoids the inefficiency caused by manually calling scripts to modify verification rules, and, by periodically polling the database table, the database only needs to be polled once within a polling time interval, avoiding the waste of computing resources caused by frequent database calls and verifications, and improving resource utilization efficiency.

The application belongs to the technical field of electronic design automation (EDA), and provides a PCB schematic diagram high-precision text recognition method and system based on multiple agents and a knowledge base. The method solves the problem of small character errors caused by the lack of understanding of electronic design professional specifications in traditional OCR, leading to circuit connection relationship misjudgment and engineering semantic failure. A field fine-tuned YOLO target detector is used for text region detection; a rotation-aware text recognition algorithm is executed on the candidate text block to generate an initial recognition result set; based on the structured PCB domain knowledge base, intelligent routing is performed: when the confidence is high and the known correct term list is met, the result is directly output, otherwise it is sent to the correction module; the correction module retrieves the knowledge base to construct a constraint prompt word through the RAG mechanism, inputs a large language model to generate a corrected text; the original result and the corrected text are weighted and fused according to the confidence of the agent, and rule consistency verification is performed; the rule checking module forces to comply with the PCB naming specification and corrects the format error.

The application discloses a macro unit automatic synthesis method based on splicable analog unit and belongs to the technical field of electronic design automation (EDA). The method aims to solve the problem that device matching constraint, layout area efficiency and design rule check cannot be considered in the existing analog layout automatic process. The method mainly comprises the following steps: receiving a circuit netlist with layout intention annotation, mapping devices into Acells; placing initial row bases according to a symmetric mode; executing a compression algorithm for keeping constraints, optimizing area by removing specific redundant polysilicon structures at the interfaces of adjacent Acells; performing legalization processing based on contact polysilicon spacing and power ground line spacing; finally, adopting a wiring method based on the satisfiability of module theory, automatically generating internal connections under the premise of ensuring geometric symmetry. The application can generate analog macro units meeting the requirements of DRC / LVS, compact in area and high in matching characteristics, and can be directly integrated into a digital layout and wiring process.

The application discloses a document intelligent sorting system and method based on size model combination, and relates to the technical field of document intelligent processing. The system comprises a template library preparation module, a single-page intelligent classification module, a first-round sorting module, a large model secondary sorting module, a result feedback module, a knowledge base management module and a model fine-tuning module. First, the document template is subjected to OCR recognition, and template directory information and keyword information are extracted to construct a template library. Then, each document page of the document to be sorted is subjected to OCR recognition, and the preliminary classification result is determined based on the cross-validation result of the template page similarity and the keyword coverage. For the classification grouping of the fixed page number template, the rule check is performed, and for the fixed page number template and the non-fixed page number template with repeated pages or missing pages, the large model is combined with the unclassified grouping data, the related document template directory and the content of each page to perform secondary sorting. Finally, the positive knowledge base and the negative knowledge base are constructed through the feedback of business experts, and the Embedding model is fine-tuned based on the positive and negative knowledge bases, so that the self-iteration upgrade of the system is realized. The application can improve the document sorting efficiency, accuracy and generalization ability, and has the continuous optimization capability.

The application provides a driver's bill automatic identification and filling method based on a multi-mode neural network, comprising the following steps: S1: extracting multi-mode features; S2: training a bill category model; S3: predicting the category of a newly uploaded bill; and S4: extracting target filling information from a bill original picture; the method matches a label text block with a neighboring text box, does not need to rely on a fixed template, can adapt to various non-standardized bills, can effectively identify and extract information from disordered format bills, and greatly improves the adaptation capability for various irregular bill in a freight scene; a multi-mode neural network is used to classify bills from a picture visual feature and a text semantic feature double mode, solves the problem that only text recognition is easy to confuse, reduces bill category identification errors; meanwhile, target label positioning, position matching and content rule checking are used to accurately extract label values, avoid information matching errors and filling confusion, and realize accurate data entry.

The application provides a kind of multi-engine cooperation's official document review method, system and related equipment, wherein, method includes first to official document structured analysis, mapping physical style attribute as structured semantic node;Then cooperatively executes three levels of check: first level deterministic rule check, for quickly screening format and punctuation error;Second level fact knowledge check, verify the accuracy of entity information with knowledge base;Third level semantic logic check, utilize large language model to process complex semantic and logic problem, when executing semantic logic check, the application constructs prompt word dynamically and injects the reasoning process of large language model by taking the results of the first two levels of check as hard constraint, can effectively solve the problem of rigid rules and model illusion in prior art, on the basis of guaranteeing format and fact accuracy, realize the identification of deep logic error, improve the quality and efficiency of official document review.

The application discloses a multi-source heterogeneous user demand and product feature matching method based on deep learning, relates to the technical field of product feature matching, and solves the technical problems that only relying on single modal data, it is difficult to understand user intention, generate personalized scripts, lack BOM rule checking and project declaration, and script and configuration matching, causing the disconnection of scripts and configurations; through the unified mapping of text, image, BOM graph structure, project declaration data and other multi-source heterogeneous features to the same dimension, and the fusion by adopting the cross-modal self-attention mechanism, the potential correlation between user demand and product features can be comprehensively captured. The full-configuration BOM rule library is modeled as a graph structure, the dependency and constraint relationship between parameters is extracted by using GNN, and the illegal items in user selection and configuration are detected; the optimal adjustment scheme is generated in combination with the error case library, the risk of subsequent links is reduced, and the compliance evaluation result is fed back to the script generation module, so that the optimal script generated is optimized.

A query processing device that reduces the calculation cost for checking whether a query complies with restrictions. A query dividing section generates subqueries by dividing an input query for each of a plurality of organizations. A score computing section computes an organization score by evaluating an organization-specific risk that is the risk of determination that the subquery does not comply with organization rules of the organization corresponding to the subquery, on the basis of history information relating to a determination track record resulting from determining, regarding each organization, whether or not the input query complies with the organization rules of each organization. A subquery control section sequentially transmits the subqueries to rule check devices in transmission order according to the organization score, and response information is received regarding the subquery from the rule check devices. Whether the input query complies with restrictions is determined by using the response information.

The application discloses a kind of based on vehicle-mounted network department mark protocol intelligent adaptation and smooth transition method, it is related to communication protocol technical field, method includes: S1, NLP protocol knowledge automation construction: NLP module parses department mark document and terminal message annotation, extracts version difference, constructs the knowledge base containing field type, bit sequence, constraint, is synchronized to rule engine;S2, AI model training, initialization and strategy library construction;S3, rule check and AI mapping: rule engine checks message format and realizes source protocol message legality check, AI module is dynamically adjusted according to scene mapping rule;S4, protocol conversion;S5, synchronous compliance inspection;S6, data reporting: data after compliance inspection is reported.It realizes protocol automatic analysis, dynamic field mapping, version smooth transition and compliance check integration, reduces adaptation cost, improves access efficiency and data accuracy.

The application provides an AI-Agent-based system-level design generation method and system. The method provided by the application comprises: receiving design requirement information input by a user; performing system-level architecture design and system partitioning on the design requirement information based on an AI-Agent to generate a system architecture scheme, design prompt information and a constraint file, and simultaneously performing feasibility verification on the system architecture scheme through a generation rule checking mechanism to obtain a system architecture scheme, design prompt information and a constraint file that pass the verification; matching a corresponding path generation method based on the design prompt information that passes the verification or Python algorithm code input by the user, generating hardware description language code based on the path generation method; and performing functional verification on the hardware description language code, and after the hardware description language code that passes the functional verification is connected with a back-end tool that passes the verification, layout and wiring are performed and a GDS-II layout file is output.

The application discloses an aero-engine software tracing and checking method and system, realizes full-process automatic tracing from requirement definition to final verification, shows the tracing relationship in an intuitive mode, improves the efficiency and quality of software development, and provides support for aero-engine software development and maintenance. The technical scheme is as follows: a link relationship is established: a plurality of requirement files and traced files are linked through different tools or methods, and the link relationship between high and low layer requirements and data is verified; after each source file with the link relationship is acquired, the source file is converted into an intermediate file through a converter, the intermediate file contains format information, the tracing relationship in the intermediate file is extracted by analyzing a keyword, and a coverage range is acquired; based on the tracing rule checking, the wrong tracing relationship is located and modified; and a visual view is formed according to the tracing relationship.