43 results about "Model modification" patented technology

The invention relates to the technical field of bridge bearing capacity evaluation, and discloses an existing continuous beam bridge bearing capacity comprehensive evaluation method which comprises the steps that multi-source data are collected to construct a three-dimensional damage voxel field, and an initial finite element model is generated; simulating a heavy load identification control section, and designing an equivalent static load test scheme according to an equivalent internal force principle; executing a field static load test, collecting elastic response data and constructing an actual measurement response vector; calculating errors and iteratively adjusting parameters in a voxel field constraint range to finish model correction; and generating an operation space-time security envelope based on the correction model, and comparing the state in real time to output a control instruction. A three-dimensional damage voxel field is constructed, voxels are used as a normalized data carrier, discrete apparent and internal damage data such as three-dimensional laser scanning point cloud, ultrasonic velocity and rebound strength are mapped into a continuously distributed space field, and the space variability of the rigidity of an existing bridge material can be represented in a refined mode. And the accuracy of describing the physical current situation of the structure by the initial finite element model is improved.

The systems and methods disclosed herein monitor application (e.g., artificial intelligence (AI) model) operations using interactions between the application and a kernel. The systems and methods disclosed herein intercept, using a kernel interface, one or more function invocations transmitted from the application (e.g., an AI model without model modification). Event record(s) are generated for one or more functions to define process identifiers, resource interaction types, timestamps, and / or resource identifiers. Observed pattern(s) for the application are identified by comparing current event record(s) with previous record(s), and the identified observed pattern(s) are evaluated against reference pattern(s) to generate score(s). Data packet(s) that indicate observed pattern(s), corresponding score(s), and / or cryptographic digital fingerprint(s) of the one or more functions are generated. The data packet(s) are transmitted to distributed ledgers for immutable storage.

The invention relates to the technical field of multi-section and multi-BIM model file boundary connection review, in particular to a BIM model-based comprehensive consultation method and system, which can be used for quickly reviewing boundary connection and developing a corresponding review system. The problems that large-scale project boundary connection is complex, multi-section and multi-model file collaboration is not smooth, and more disassembly and modification are generated in the construction process are solved. According to the method, the BIM components related to boundary connection are pre-selected for highlight display or specific color setting, and the boundary connection of the model is pointedly examined. Through a multi-segment model boundary connection review opinion and model view angle association function, a space-time label and a VR view angle synchronization function, a problem component in a multi-segment multi-model file is quickly searched, and a review model modification condition is quickly checked; a new and old component mapping relation is automatically established by comparing characteristic values such as vertex coordinates and normal vectors, and automatic inheritance of highlight setting of updated components is achieved; and collision and disconnection pre-check is performed by using a spatial index algorithm, so that the review efficiency is improved.

The invention relates to the technical field of computer simulation, and provides a BIM (Building Information Modeling)-driven green performance real-time simulation analysis system, which is characterized by comprising a model analysis module used for importing and analyzing an original BIM file and extracting multi-source building component data; the model conversion module is used for constructing a unified scene model; the parameter association module is used for generating and outputting a synchronization parameter update package; the simulation calculation module is used for outputting a green performance index distribution diagram; and the interaction feedback module is used for converting the green performance index distribution diagram into a hot area visualization diagram, superposing and rendering the hot area visualization diagram into a unified scene model in real time, and when the user interaction operation is model modification and / or parameter analysis, generating a parameter modification instruction and sending the parameter modification instruction to the parameter association module so as to trigger a new round of simulation. Through a multi-source data dynamic fusion mechanism and a parameter bidirectional link technology, an interactive feedback closed-loop system from a BIM model to green performance analysis is constructed.

This invention provides an information processing device and a model modification method that improve the accuracy and reliability of radio wave propagation models. [Solution] The method involves acquiring a radio wave propagation model having a radio wave propagation area in a virtual space and objects within the area having predetermined radio wave propagation characteristics, acquiring radio wave propagation path information and reception level information for each receiving point in the model based on the simulation results of radio wave propagation, acquiring radio wave direction of arrival information and reception level information for each actual measurement candidate position in real space corresponding to the receiving point, deriving the difference between the reception level at the first receiving point and the reception level at the corresponding first actual measurement candidate position, extracting the second receiving point with the largest difference among the first receiving points, deriving the first direction of arrival received at the second actual measurement candidate position with the maximum reception level based on the direction of arrival information at the corresponding second actual measurement candidate position, extracting the first path that has a direction close to the first direction of arrival among the paths passing through the second receiving point, and correcting the radio wave propagation characteristics of objects on the first path.

The invention discloses an undercarriage beam model parameterization modeling method and device, a medium and a product, the method adopts Excel to construct part parameters in a part-level beam model, and quick modeling and efficient rigidity adjustment are realized by calling the part parameters; compared with a traditional manual modeling mode in which re-modeling is needed in single model modification, the process is tedious and the efficiency is low, the method has the advantages that the iteration efficiency of part parameters can be remarkably improved, the beam model parameter debugging period is greatly shortened, and powerful support is provided for efficient optimization of a design scheme.

The invention provides a model conversion method and device and a storage medium. The method comprises the steps of receiving a model conversion request sent by a client based on a designer canvas; the model conversion request comprises a domain model and a model type to be converted; loading a model conversion engine; calling a model conversion engine to convert the domain model into an application class model under the model type; and if the conversion is completed, storing the application class model into a model database. According to the embodiment of the invention, through a mechanism of converting the application model from the domain model and in cooperation with recording and storage functions of the conversion operation, tracing of the model modification history is realized, the user is guided to complete configuration selection and data input through the built-in and predefined model conversion engine, operations such as manual compiling of complex conversion scripts by the user are reduced, and the user experience is improved. The technical operation threshold is greatly reduced, omission or errors possibly caused by manual synchronous operation are effectively reduced through the mechanism, and the consistency maintenance level between different abstract levels is remarkably improved.

The application discloses a feature-based rapid design modeling method for an aircraft structural member, which comprises the following steps: feature decomposition, feature structure analysis, feature template establishment, feature constraint creation, feature instantiation, feature surface simplification and correction, feature information extraction, generation of an assembly symmetric counter-piece and a non-complete assembly symmetric counter-piece, so that the computer can automatically create the relevant constraints between the base body and the created features by recognizing the position information of the created features and the base body, automatically generate the features by driving the CAA template program, freely modify the feature size parameters according to the user demand or increase or decrease the features on the original geometric body by Boolean operation to complete the variant design of the part, and freely extract the feature parameter information, thereby improving the freedom of the model modification of the aircraft structural member by the designer and the design efficiency of the aircraft structural member.

The systems and methods disclosed herein monitor application (e.g., artificial intelligence (AI) model) operations using interactions between the application and a kernel. The systems and methods disclosed herein intercept, using a kernel interface, one or more function invocations transmitted from the application (e.g., an AI model without model modification). Event record(s) are generated for one or more functions to define process identifiers, resource interaction types, timestamps, and / or resource identifiers. Observed pattern(s) for the application are identified by comparing current event record(s) with previous record(s), and the identified observed pattern(s) are evaluated against reference pattern(s) to generate score(s). Data packet(s) that indicate observed pattern(s), corresponding score(s), and / or cryptographic digital fingerprint(s) of the one or more functions are generated. The data packet(s) are transmitted to distributed ledgers for immutable storage.

The application provides a game scene generation method and device, computer equipment and a storage medium. The method comprises: generating an initial game scene according to model position information corresponding to a three-dimensional model; reading a hierarchical relationship between three-dimensional models in response to a model modification instruction for a target model; determining an associated model corresponding to the target model according to the hierarchical relationship; and modifying the target model and the associated model according to the model modification instruction to obtain a target game scene. The method provided in the application embodiment can read the hierarchical relationship between models from a preset modeling software after receiving a model modification instruction for a target model in a game engine, thereby determining the associated model corresponding to the target model in the initial game scene of the game engine, completing the synchronous modification of the target model and the associated model, effectively avoiding the problem of scene disorder caused by the loss of model information, and improving the creation efficiency of the game scene.

A system, method, and computer program product for implementing deep learning software model modification is provided. The method includes monitoring operational performance of a software model. An expected confidence level associated with the operational performance is first determined and it is determined that an inference associated with the expected confidence level is below a selected range of inferences associated with assigning new feature data as candidate video data. A candidate sequence comprising video data associated with the candidate video data is received and a similarity between frames of the candidate sequence is determined. A frame comprising a highest similarity with respect to segments of candidate video data is selected and it is detected that the frame is not associated with additional frames stored within a full cache structure. The software model is retrained such that the operational performance is modified.

The application discloses a difference calibration method and device of an engine controller and electronic equipment, and comprises the following steps: determining whether a calibration data version corresponding to a controller is updated, determining new difference information of the controller in the case that the calibration data version is updated, wherein the controller comprises a main controller and a secondary controller; determining a difference calibration quantity of the controller based on the new difference information, generating target code according to the difference calibration quantity, and inserting the target code into a software integration baseline to obtain target calibration software; and calibrating the main controller and the secondary controller by the difference calibration quantity based on the target calibration software. The application can greatly improve the development and calibration efficiency, avoid meaningless repeated model modification, and improve software reliability by identifying the requirement of differential calibration, realizing the differential calibration quantity function value in the mode of automatic code without modifying the model and increasing the calibration quantity.

The application relates to a kind of Modelica model-oriented incremental compilation method and system, the method comprises: the abstract syntax tree of Modelica model is obtained by keyword matching to the Modelica model text edited and modified;Abstract syntax tree includes the definition and behavior of each component in Modelica model;Determine the changed part of Modelica model editing and modification based on abstract syntax tree and the change of last time;The intermediate representation of the changed part of Modelica model is instantiated;Intermediate representation includes: the argument tree of component and component behavior list;The intermediate representation of the changed part and unchanged part of Modelica model is integrated, and the complete representation of Modelica model is obtained;Through incremental compilation, the modified part of model can be quickly identified and locally compiled, so that the whole model is avoided to be recompiled, and the compiling efficiency is significantly improved.At the same time, incremental compilation can also effectively reduce the output of compiling diagnosis information, so that users can more easily obtain the diagnosis information related to the modified part, and further improve the modeling experience.

The disclosure relates to identifier-based tracking and verification of machine learning model modifications, and in various examples, tracking and verifying modifications of a machine learning model using a unique identifier are described herein. For example, the systems and methods described herein may generate unique identifiers, such as checksums, hashes, etc., that track modifications to the model. For example, if a first version of the model is modified to generate a second version of the model, such as by performing fine tuning, optimization, quantization, and / or any other modification technique, data representing the modification may be obtained. The data may then be used to generate information describing the modification. Additionally, information may be encoded using one or more encoders and / or processed using one or more algorithms to generate a unique identifier for the second version of the model. The present disclosure also describes systems and methods for performing various tasks using unique identifiers.

The systems and methods disclosed herein monitor application (e.g., artificial intelligence (AI) model) operations using interactions between the application and a kernel. The systems and methods disclosed herein intercept, using a kernel interface, one or more function invocations transmitted from the application (e.g., an AI model without model modification). Event record(s) are generated for one or more functions to define process identifiers, resource interaction types, timestamps, and / or resource identifiers. Observed pattern(s) for the application are identified by comparing current event record(s) with previous record(s), and the identified observed pattern(s) are evaluated against reference pattern(s) to generate score(s). Data packet(s) that indicate observed pattern(s), corresponding score(s), and / or cryptographic digital fingerprint(s) of the one or more functions are generated. The data packet(s) are transmitted to distributed ledgers for immutable storage.

The systems and methods disclosed herein monitor application (e.g., artificial intelligence (AI) model) operations using interactions between the application and a kernel. The systems and methods disclosed herein intercept, using a kernel interface, one or more function invocations transmitted from the application (e.g., an AI model without model modification). Event record(s) are generated for one or more functions to define process identifiers, resource interaction types, timestamps, and / or resource identifiers. Observed pattern(s) for the application are identified by comparing current event record(s) with previous record(s), and the identified observed pattern(s) are evaluated against reference pattern(s) to generate score(s). Data packet(s) that indicate observed pattern(s), corresponding score(s), and / or cryptographic digital fingerprint(s) of the one or more functions are generated. The data packet(s) are transmitted to distributed ledgers for immutable storage.

The embodiment of the invention provides a data set labeling method, electronic equipment, a storage medium and a program product. The method comprises the steps of deploying an open source data set labeling model to a preset container cluster and / or deploying a preset artificial intelligence model to the preset container cluster according to model modification parameters; the effective data set is uploaded to object storage for segmentation and encryption storage, and a to-be-labeled data set is obtained; according to the labeling task information, when it is detected that a labeling mode is model labeling, calling a to-be-labeled data set according to the labeling task information, and calling a preset artificial intelligence model and / or an open source data labeling model from a preset container cluster as a target labeling model; decrypting the data set to be labeled; and inputting the decrypted data set into the target labeling model to generate labeled data, and storing the labeled data into the object storage. According to the method, automation and configurability of the labeling process are achieved, and high flexibility and safety are achieved.

This application relates to the technical field of aero-engine modeling and simulation, and in particular to a model lightweighting method, apparatus, computer equipment, medium, and program product. The method includes: after obtaining a modified model obtained by modifying an initial model, identifying parts in the modified model to obtain its configuration file; comparing the configuration files of the initial model and the modified model to determine the modified parts based on the comparison results; performing lightweighting processing on the target model to obtain a lightweight model corresponding to the target model; and calling a rendering engine to render the configuration information of the modified parts and the lightweight model in the initial rendering model to obtain the target rendering model corresponding to the modified model. Using the method of this application can improve the efficiency of aero-engine modeling and simulation.

The application provides a hull model traceable modification control method, system, medium and electronic equipment, the method comprises the following steps: entering a hull model display interface based on a preset software, the preset software comprises Tribon software; modifying the hull model based on user operation data, the modification content comprises plate thickness, length, through hole, shape and notch hole; after completing the hull model modification, performing a part separation operation to generate a target file, the target file comprises a wcog file; based on user demand, performing a filtering operation on the GPS4 column of the target file to locate and output the target part. The application can accurately record the modification history of each part, which facilitates designers to quickly and clearly understand the modification status of the part in subsequent work, greatly improves the traceability of the design, and quickly locates the part that needs to be paid attention to in subsequent work, greatly reduces the time for finding and screening the part, thereby improving the overall work efficiency and reducing the production cost.

The application provides a bridge substructure adaptive modeling and updating method, comprising the following steps: S1: bridge substructure adaptive object definition and bridge substructure component adaptive object definition; S2: bridge substructure adaptive object creation and bridge substructure component adaptive object creation; S3: bridge substructure adaptive modeling and bridge substructure component adaptive modeling; S4: bridge substructure modification and adaptive updating, bridge substructure component modification and adaptive updating. The application improves the efficiency of bridge substructure three-dimensional modeling and model modification, reduces the workload of modeling in the man-machine interaction mode, shortens the cycle of bridge substructure three-dimensional modeling, and provides a fast means for engineering designers.

This document describes, through various examples, the process of updating model maps with information associated with modifications to machine learning models. For instance, the systems and methods described herein can automatically update model maps with additional information about modifications made to models. To update a model map, the unique identifier can be used to identify that a modification has been made to a model—such as through fine-tuning, optimization, quantization, and / or another modification technique—to generate a new version of the model. Additional information about the modification is then gathered, such as by decoding the unique identifier, testing the new version of the model, and / or using data that describes how the model was modified.The model map can then be automatically updated with the additional information. Furthermore, this process can be repeated if additional modifications are made to the model to generate new versions of the model.

1. The name of the design product: ruler (fixed width). 2. The use of the design product: used for auxiliary model modification tools. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.

This invention belongs to the field of watermark data processing technology, and relates to a method and system for generating zero-watermark 3D models of cultural relics. It actively aligns the point clouds of the 3D model of the cultural relic through an embedded spatial transformation network, avoiding instability in feature extraction caused by differences in the initial pose of the model. By aggregating local neighborhood geometric information through multi-scale grouping and attention mechanisms, it generates deep feature vectors, improving the ability to distinguish complex geometric deformations. This makes the extracted deep feature vectors robust to geometric transformations and highly discriminative. Binarization and error-correcting coding generate fault-tolerant binary fingerprints, enabling the extraction of robust deep features without modifying the original model. This solves the technical problems of traditional watermarking requiring model modification leading to loss of accuracy in the 3D model of cultural relics, and the weak feature expression and poor anti-attack capabilities of existing zero-watermarking methods. It achieves high-fidelity and robust zero-watermark generation of 3D models.

An estimation device 1 for estimating the extent of river plume comprises: a model modification unit (133) that acquires a trained SSM which was pre-trained using image data pairs (data pairs for pre-training), and constructs a first SSM in which the trained SSM is changed such that a final layer is composed of the two classes of river plume and non-river plume; a model training unit (135) that acquires other image data pairs (data pairs for transfer learning) consisting of a plurality of satellite images and data in which tags indicating river plume and non-river plume are added to regions obtained by dividing each satellite image into prescribed unit regions, and constructs a second SSM for estimating the extent of river plume by inputting the other image data pairs to the first SSM and performing machine learning; and an inference unit (14) that inputs a target satellite image for estimation to the second SSM and estimates the extent of the river plume included in the target satellite image for estimation.

The invention discloses a digital twinning-based constructional engineering full-life-cycle intelligent collaborative management system, and relates to the technical field of constructional engineering management. The system comprises a model construction module, a data screening module, a model adjustment module and a collaborative management module, wherein the model construction module constructs a construction engineering full life cycle model based on engineering data of each stage of a construction engineering full life cycle; the data screening module is used for executing dynamic screening processing of engineering data detail levels and dynamic evaluation processing of engineering data complexity; the model adjustment module is used for executing stage self-adaptive adjustment processing and detail level self-adaptive adjustment processing of the building engineering full life cycle model; and the collaborative management module receives the constructional engineering full-life-cycle model adjusted by the model adjustment module, and when a model modification request is received, intelligent collaborative management of the constructional engineering full-life-cycle model is executed based on a collaborative management demand of the model modification request.

This invention belongs to the field of decoration engineering technology, specifically relating to a BIM-based collaborative management method for decoration supply chain data. By generating product IDs containing codes, models, and parameters, and establishing a unique binding relationship between these IDs and BIM model components, deep integration of model data and supply chain information is achieved. Furthermore, a checksum mechanism is used to detect discrepancies between model modifications and inventory changes. When discrepancies exceed a threshold, backtracking is triggered to accurately locate and repair abnormal nodes. This method effectively improves the synchronization efficiency and data consistency between the BIM model and the supply chain database, solving collaboration obstacles caused by information asynchrony and version inconsistencies, and providing reliable data support for the digital management of decoration projects.

This invention provides an integrated design and manufacturing process method for hydraulic support parts. The method includes: Step 1) Creating model features corresponding to the part's machining processes; Step 2) Extracting the corresponding machining process names and parameters and saving them to the model's parameters; Step 3) Automatically matching the extracted machining process names using a process route knowledge base to form a unique process route containing all main machining processes and saving it to the model's parameters; Step 4) Updating and saving the part model when modified in the CAD system; Step 5) Checking the data into the Windchill system's data pool for verification and feedback modification; and Step 6) Automatically generating the design and manufacturing process of the hydraulic support parts. This method offers advantages such as automatic calculation of main material quotas for parts, automatic creation of process routes, automatic generation of equipment and work centers, automatic calculation of working hours, high efficiency in MBD parameterization of the part's 3D model, and reusability.

1. Name of the designed product: model section (hollow pipe). 2. Use of the designed product: used for model modification or model processing. 3. Design points of the designed product: in shape. 4. Picture or photo showing the design points: perspective view.

The application relates to the technical field of bridge bearing capacity evaluation, and discloses a kind of comprehensive evaluation method of bearing capacity of existing continuous girder bridge, comprising the following steps: collecting multi-source data to construct three-dimensional damage voxel field, generating initial finite element model;Simulate heavy load identification control section, design equivalent static load test scheme according to equivalent internal force principle;Performing field static load test, collecting elastic response data and constructing measured response vector;Calculate error and iteratively adjust parameters within the constraint range of voxel field, complete model modification;Generate operation space-time safety envelope based on the modified model, and compare state output control instruction in real time.Through the construction of three-dimensional damage voxel field, the voxel is used as the normalized data carrier, and the discrete apparent and internal damage data such as three-dimensional laser scanning point cloud, ultrasonic velocity and rebound strength are mapped into continuous distribution space field, which can finely represent the spatial variability of the material stiffness of the existing bridge. The accuracy of the initial finite element model in describing the physical status of the structure is improved.

In various examples, updating model cards with information associated with modifications to machine learning models are described herein. For instance, systems and methods described herein may automatically update model cards with supplemental information about modifications that occur to models. To update a model card, the unique identifier may be used to identify that a modification occurred to a model—such as by performing fine-tuning, optimization, quantization, and / or any other modifying technique—in order to generate a new version of the model. Supplemental information about the modification is then obtained, such as by decoding the unique identifier, testing the new version of the model, and / or using data describing how the model was modified. The model card may then automatically be updated with the supplemental information. Additionally, this process may continue to repeat as additional modifications occur to the model to generate new versions of the model.