18 results about "Material Description" patented technology

The invention provides a redundant material data cleaning system based on a large model, belongs to the technical field of industrial intelligence and data governance, and realizes end-to-end semantic cleaning by utilizing the deep semantic understanding capability of a pre-trained large language model. Material description is converted into a high-dimensional semantic vector, semantic similarity is accurately calculated in a unified vector space, materials with the same essence are recognized beyond literal difference, and redundant items are automatically merged through intelligent clustering. The method not only can deeply capture semantic association between core attributes and effectively neglect noise, but also has the potential of fusing structured attributes to perform more robust judgment, significantly improves cleaning precision and efficiency, and overcomes inherent limitations of a traditional assembly line method.

The invention provides an automatic material identification and matching method and system for a three-dimensional model and a medium, and relates to the technical field of material management, and the method comprises the steps: constructing a standardized material database, and extracting and standardizing material attribute information; analyzing first material description information in the three-dimensional software model by utilizing an SQL (Structured Query Language), and matching the first material description information with the material attribute information to obtain a first material matching result; extracting second material description information in the project material document by using VBA programming, and matching the second material description information with the material attribute information to obtain a second material matching result; and data integration is carried out through PowerBI, and a project material state visual billboard is constructed. The technical problems that in the prior art, a unified standardized material database is lacked, material description formats in different sources are inconsistent, expression is not standard, a construction material list cannot be accurately generated, and informatization and intellectualization of project material management are limited are solved.

The invention discloses an intelligent material information management method and device based on LangGraph and multiple agents. The method comprises the steps that an unstructured material description text input by a user is acquired; calling a preset LangGraph state diagram to drive a plurality of agents to perform feature analysis, attribute extraction, multi-level category classification and attribute standardization on the unstructured material description text according to a preset workflow; and obtaining multi-level category analysis information and standardized attribute data of the material to form structured material description data, and storing the structured material description data. According to the method, the LangGraph state diagram technology is innovatively adopted to construct a multi-agent processing assembly line, all agents achieve information transmission and cooperative work by sharing the SkuState state, and automatic structured processing, intelligent classification and standardized management of material data are achieved.

The invention discloses a material standardization method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of obtaining material description content, and determining at least one input type corresponding to the material description content; aiming at each input type, determining type content of the material description content aiming at the input type; extracting a type text corresponding to the type content; combining the type texts corresponding to the input types to generate a combined description text corresponding to the material description content; extracting at least one attribute key value pair from the combined description text; wherein the attribute key value pair comprises an attribute name and an attribute value; and according to the at least one attribute key value pair, matching a standard material corresponding to the material description content from a standard material library. According to the embodiment, the material description content can be subjected to standardization processing, the problem of material identification errors is reduced, and the product quality and equipment safety of enterprises are guaranteed.

The invention relates to the technical field of artificial intelligence, and provides an electronic component library management method based on AI, which can carry out continuous mask language model training on a BERT layer in BERT-BiLSTM-CRF, reduces the difficulty of subsequent training while enhancing the adaptability of domain data, and improves the context semantic understanding ability at the same time. Multi-granularity feature fusion is performed based on a multi-granularity priori knowledge fusion attention mechanism, so that the model is more comprehensive and focuses on key features, and the accuracy of the model is improved; the electronic component entity extraction model is used for performing entity extraction on a target material description text, so that the dependence on a fixed separator and a hard coding rule is eliminated, the material description text in any format can be processed, and the adaptability problem of component description fragmentation and term density is solved; and the library field increment is updated to the electronic component library, so that automatic and efficient management of the electronic component library is realized.

The application provides a material construction plan quantity generation method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining a BIM model, wherein the BIM model comprises components and component types, component attributes and component quantities of the components, and the component attributes comprise a plurality of attribute parameters; determining a material type matched by the component type corresponding to the component quantity according to a preset material type matching rule; determining which attribute parameters in the component attributes are associated attribute parameters according to the matching relationship between the component type and the material type; generating a material description string by using the material type and the associated attribute parameters; determining a target material corresponding to the material description string in a pre-stored industry material dictionary; and determining a construction plan quantity of the target material according to the component quantity. Through the application, component material data unification and automatic matching can be realized, time consumption can be reduced, and errors can be avoided.

The invention belongs to the technical field of airplane digital structure design, and discloses a batch material description loading method and system.The method comprises the steps that in each part of a module, a rectangular coordinate system attached to the surface of the part is automatically created according to a machining method of the part; obtaining a part envelope based on the coordinate system, and calculating length, width and height information; and automatically loading the material description according to the envelope information. The invention provides a self-adaptive coordinate system creation strategy aiming at four machining modes of machining, plates, profiles and composite materials, and particularly for machining parts, the machining parts are intelligently processed according to three conditions of extreme value surface conditions. The system comprises a coordinate system creation module, an envelope calculation module and a material loading module. Accurate, efficient and batch loading of material description is achieved, the defects that in the prior art, measurement errors are large, and the automation degree is low are overcome, and the airplane modular design efficiency and the data quality are remarkably improved.

The invention relates to a three-dimensional material generation method and device, equipment and a medium, and the method comprises the steps: obtaining material description information in response to an input operation in a session page, the material description information is used for describing task contents of a material generation task, the material generation task comprises a plurality of task nodes, and the task nodes are used for generating a plurality of data; the plurality of task nodes have an execution sequence relationship; an editing page of the first task node is displayed, the first task node belongs to one of the multiple task nodes, the editing page comprises a first material element of the first task node, and the first material element is obtained based on the material description information; in response to an adjustment operation on the first material element in the edited page, obtaining a second material element of the first task node; and in response to completion of execution of the material generation task, displaying a first material, the first material being a three-dimensional material, the first material being obtained based on the second material elements corresponding to the plurality of task nodes. And the generation efficiency and precision of the three-dimensional material are improved.

The invention is suitable for the technical field of data management, and provides a material master data semantic matching method and system based on word vector similarity, and the method comprises the following steps: S1, constructing a standard library; S2, preprocessing data: carrying out word segmentation and preprocessing on material master data and text data in the standard library; s3, word vector generation: utilizing a natural language processing technology to generate word vectors for the material main data and words or phrases in the standard library; and S4, similarity calculation: calculating the similarity between the word vector of each material description and characteristic in the material main data and the word vector of the text data in the standard library. According to the word vector similarity-based material master data semantic matching method and system provided by the scheme, the matching accuracy and flexibility are improved, material descriptions with similar semantics but different expressions can be processed, and the matching precision and efficiency are further improved by optimizing the matching result.

The invention provides an artificial intelligence-based material main data intelligent cleaning method, which comprises the following steps: obtaining a material description text, extracting text features through a multi-modal feature extraction strategy, and disassembling material description according to a classification template, the material description comprising a technical name, a specification parameter, a measurement unit and material data; material description is obtained, equivalent description conversion is carried out through a corresponding synonym database, missing attributes are pre-judged based on the industry knowledge graph, and material information is generated; material information of the multiple groups of material description texts is obtained, various descriptions in the material information are compared, if the material descriptions are in one-to-one correspondence, the material information is combined, a counting strategy is preset, and the number of the combined material information is obtained; by obtaining original material description and AI material description subjected to AI processing, the difference between the original material description and the AI material description is analyzed, a semantic equivalence rule is generated, and a synonym database is updated.

This application discloses a method, apparatus, device, and storage medium for archiving electronic component materials, relating to the field of computer software technology. The method includes: obtaining material categories based on the electronic component's specification document (SMD); determining the file type of the SMD based on preset keywords and the material category, wherein the file type includes individual material files and material series files; determining a target area from the SMD according to the file type, and extracting component parameters based on the material category and the target area; and generating and archiving a target material description based on the component parameters and the material category. This method solves the technical problem of low accuracy in information extraction from specification documents due to the inability to automatically identify material series files, resulting in extracted parameters containing multiple sub-model information. It achieves accurate matching of extracted component parameters with currently archived materials, improving the accuracy of parameter extraction and the usability of archived data.

The application discloses a kind of 3D design auxiliary methods based on multimodal input and intelligent optimization, comprising: obtaining text data to be processed and image data to be processed;Text data to be processed and image data to be processed are respectively extracted features, and text features and image features are obtained;The text features include size description, functional description, material description and structure description;The image features include image structure features;The text features and the image features are fused, and the fusion features are obtained;Based on the fusion features, several 3D models are constructed;Based on the preset design rule and the text features, a knowledge graph is constructed, each 3D model is evaluated based on the knowledge graph, and the optimal 3D model is determined based on the evaluation result.The technical solution disclosed in the application significantly improves the generation efficiency and accuracy of 3D model.

The invention discloses a material main data intelligent classification method, which comprises the following steps: obtaining historical material description data with marked material types in advance, forming a training set and a test set, generating a text vector for material description for classification model training, and determining a reference confidence threshold according to test performance; the method further comprises the steps of generating a to-be-predicted vector according to a to-be-classified material description text received in real time, and obtaining a predicted material type and a corresponding prediction confidence coefficient based on the classification model; and based on the performance index parameters of multiple classification predictions in the historical time sliding window, adjusting the reference confidence coefficient threshold so as to compare the reference confidence coefficient threshold with the prediction confidence coefficient of real-time prediction, and determining a prediction result. According to the method, the confidence coefficient threshold value is dynamically adjusted based on the performance indexes in the historical time sliding window, so that the classification system can adapt to the state change of the service data, manual recheck resources are intelligently allocated on the premise of ensuring the accuracy, and the balance between efficiency and precision is realized.

The invention provides a ship construction data collaboration method and system based on a unified material code, and the method comprises the steps: carrying out the three-dimensional modeling of a general station, delivering the ordering information needed by the ordering of a general assembly factory, and forming an ordering data table; and then converting the material description of the general station into the material description of the general assembly factory by establishing a standardized mapping rule to obtain a general station and general assembly factory material information mapping relation table commonly used by both parties. And on the basis, the general assembly factory receives the order data table of the general place and issues an order list according to the order data table, and finally, the general assembly factory receives the general place design model and carries out collaborative revision and confirmation on the order data according to actual manufacturing requirements. According to the data collaboration method, the collaboration problem caused by inconsistent material codes between an overall design unit and a production and manufacturing unit is effectively solved, the efficiency and accuracy in the design and manufacturing process are improved, rework and delay are reduced, and the data collaboration method has important industrial application value.

The invention provides a nuclear power equipment material description generation method, electronic equipment and a computer program product. Relates to the technical field of nuclear power. In view of the problem of low material description accuracy of traditional nuclear power equipment, the nuclear power equipment material description generation method provided by the invention comprises the following steps: acquiring image information of the nuclear power equipment; inputting the image information into an image coding sub-network, and extracting a first target feature vector of the image information based on the image coding sub-network; inputting the first target feature vector and a term set in a preset description text library into a term-aligned connection sub-network, and performing term matching and feature fusion processing based on the term-aligned connection sub-network to obtain a second target feature vector; and inputting the second target feature vector and the dynamic cue word into a multi-modal large language model, and processing based on the multi-modal large language model to obtain a first material description text of the nuclear power equipment. According to the embodiment of the invention, the material description accuracy of the nuclear power equipment can be improved.

The invention provides a virtual resource generation method and device, electronic equipment and a storage medium, and belongs to the technical field of computers. The method comprises the steps that in response to an input operation on material description information, a first special effect material output by a generation model is displayed through the generation model matched with the material description information, the material description information is used for describing the form of the special effect material, and a main body and a special effect in the first special effect material are displayed in the form; and in response to a resource generation operation based on the first special effect material, displaying a generated virtual resource, the virtual resource being a data packet used for displaying the first special effect material in the live broadcast room. The generation model is a special model matched with the material description information, so that compared with a general generation model, the generation model has higher understanding capability on the material description information, and by applying the generation model, a user does not need to frequently input an instruction to correct the output content of the model, so that the overall generation efficiency is improved, and the user experience is improved. And the requirement of the live broadcast room for quickly renewing the virtual resources can be met.

The application discloses a building carbon emission decision-making method and device based on a whole life cycle, equipment, a medium and a product, and the method comprises the following steps: acquiring a plurality of design schemes of a large-space public building and corresponding morphological parameters; performing parameterized modeling and model translation on the morphological parameters to obtain a morphological description model and a material description model; calculating the carbon emission data of each design scheme of the large-space public building year by year in the whole life cycle according to the energy consumption data of the morphological description model and the material data and the carbon emission factor of the material description model; calculating the weight of each life cycle stage of each design scheme year by year according to the carbon emission data of each design scheme year by year, and obtaining a weighted matrix; and sorting the design schemes according to the weighted matrix, and selecting the optimal design scheme according to the sorting result. By adopting the embodiment of the application, carbon emission calculation can be performed in the early stage of building design, and the optimal scheme in terms of carbon emission performance can be evaluated and decided, which is helpful for building energy-saving and carbon-reducing buildings.

The present application discloses a material sorting method, system, equipment and medium based on a robotic arm, and the technical field to which it belongs is robotic arm control technology. The material sorting method based on the robotic arm includes: obtaining a current scene image of the working area, and obtaining material description information of the target material; segmenting the current scene image according to the material description information to obtain a material area and a material segmentation mask; performing posture estimation according to the position of the material area and the material segmentation mask to obtain a grasping posture; obtaining a standard posture of the target material, and determining the grasping position of the end effector for the target material according to the grasping posture and the standard posture; controlling the robotic arm to grasp the grasping position of the target material with the grasping posture, adjusting the posture of the end effector so that the grasped target material is in the standard posture, and performing a sorting operation on the target material. The present application can enable the robotic arm to adapt to complex sorting scenarios and improve the working accuracy and efficiency of the robotic arm.