341 results about "Model management" patented technology

A platform for dynamically generating application experiences. The platform comprises a design management system, an agent orchestration system, an analytics system, a model management system, a user management system, and databases for storing design elements and templates. The design management system provides a portal for application owners / designers to create UX / UI designs, allowing them to select design elements from a set of categories or templates. The platform gathers existing websites / applications to identify common design patterns, stored in a design catalogue database, and suggests historical interfaces for design exploration. It enables the generation of templated applications that integrate with legacy systems. The agent orchestration system parses user specifications, selects generative AI systems, and generates UX / UI content based on the specifications. The analytics system collects and analyzes data to provide insights for improving UX / UI design and optimizing website performance. The model management system trains and maintains generative AI models used for content generation.

The disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate. A UE transmits information on at least one first artificial intelligence (AI) / machine learning (ML) model, wherein the information on the at least one first AI / ML model includes a list of AI / ML models, and wherein an AI / ML model included in the list of AI / ML models is identified by a first AI / ML model identifier (ID), receives at least one AI / ML model information indicating at least one AI / ML model to be activated, wherein the at least one AI / ML model to be activated is identified by a second AI / ML model ID; and activates the indicated at least one AI / ML model based on the received at least one AI / ML model information.

The invention relates to the technical field of financial risk control, and discloses a telecommunication fraud risk identification method based on a bank card transfer scene. The method comprises the following steps: a basic feature construction stage: acquiring multi-source data of historical victim users, extracting multi-dimensional features, and processing the multi-source data into standardized time sequence data through feature coding and a DTW algorithm; in the multi-modal fusion and adversarial learning stage, a core layer containing a multi-modal analysis engine, a risk reasoning model and an adversarial generation model is constructed, and multi-modal feature fusion, risk probability output under an RLHF framework and simulated fraud feature generation driven by WGAN-GP are achieved; in the strategy output stage, risk scores are mapped through a double-layer scoring system, and three-level interception is triggered; in the model management stage, model iteration is achieved by means of a monitoring instrument panel and a rolling time window, the online effect is guaranteed by combining gray release and A / B testing, the telecommunication fraud in the transfer scene can be accurately recognized, and the risk control efficiency is improved.

The invention discloses a Java-based large language model dynamic adaptation method and system, belongs to the technical field of artificial intelligence, and aims to solve the technical problems of overcoming the interface difference of multiple model interfaces, simplifying the development process and providing standardized and high-expansibility large model management. Comprising the following steps: providing a model registration and dynamic loading service, a protocol conversion and parameter standardization service and a load balancing and failover service; a streaming transmission protocol service, a function call dynamic injection service and a global error processing mechanism are provided; when a user provides a document analysis and partitioning service, a vectorization index construction service and an RAG enhanced generation service to ask questions, relevant document blocks in the Pinecone are retrieved through the RAG enhanced generation service to serve as contexts to be injected into cue words of the large language model, and answers generated by the large language model are returned.

Methods, systems, and devices for wireless communication are described. A radio access network (RAN) node may receive a message including meta-information of a machine learning model for operation by one or more devices within a coverage area of the RAN node (e.g., supported by the RAN node), where the machine learning model may be transparent to the RAN node. The meta-information may include suitability information for control and management of the machine learning model by the RAN node. In some examples, the RAN node may receive meta-information from various logical functions. In some other examples, the RAN node may receive meta-information from one or more devices. In response to receiving the meta-information, the RAN node may send a model management message that instructs a device of the one or more devices to perform a model management operation for the machine learning model.

The invention provides an AI model management method and system based on dynamic NFT, and the method comprises the steps: firstly packaging the core elements of an AI model into on-chain intelligent assets through the dynamic NFT, and achieving the clear definition and credible storage of the ownership of the model; then, a programmable smart contract bound with the dynamic NFT is utilized to support flexible definition of an atomization authorization rule, and traditional fragile API key authorization is replaced; and finally, forcibly recording a father-son relationship in a model iteration process through a dynamic NFT chain derivation mechanism to form a non-tampering version pedigree map, and solving the problems of attribution dispute and technical source tracing of the fine tuning model. According to the invention, property right clarification, authorization control flexibility and version management credibility of AI model digital assets are realized, and the method is suitable for transaction, circulation and governance scenes of AI assets such as large language models and vertical field special models.

A communication method and a related device, in the method, under the condition that different models deployed by different communication devices are used for jointly completing the same AI task, a first communication device can determine whether to adjust the different models based on the condition that the performance of the different models meets (or does not meet) conditions, so that the different models can be adjusted. Therefore, the model management of the model is realized. In some implementation modes, the first communication device can determine third information used for adjusting the first model and / or adjusting the second model based on the first information and the second information, so that the scheme can be applied to a scene of distributed multi-node cooperative processing of the same AI task, and furthermore, the scheme can be applied to a distributed multi-node cooperative processing of the same AI task. According to the method, the node with the fault can be accurately judged based on the condition that the performance of different models meets the condition (or does not meet the condition), the influence on the whole distributed system is avoided, redundant operation caused by adjustment of fault-free equipment is also avoided, and the model management efficiency is improved.

The invention discloses a financial monitoring system based on real-time data processing and intelligent analysis, and relates to the technical field of financial information, and the system comprises a bill collection module which employs a configuration API interface, carries high-concurrency data streams through a distributed message queue, carries out the real-time connection of an upstream business system and a financial system, and receives bill detail data; and the analysis and check task arrangement module manages the task dependency relationship based on a directed acyclic graph model, and arranges a data pulling task, a bill general task and a bill check task according to a preset rule. According to the financial monitoring system provided by the invention, the automation and intelligence level of financial management is remarkably improved by integrating real-time data processing and intelligent analysis technologies, the system adopts a configured API interface and a distributed message queue, efficient butt joint with an upstream business system and a financial system is realized, and the financial management efficiency is improved. The real-time performance and accuracy of data receiving are ensured, and the data processing flow is more flexible and controllable.

The model management device includes a communication unit capable of communicating with a plurality of AI devices, each of which continuously performs training of a machine learning model, and a processor configured to manage training of a machine learning model in each of the plurality of AI devices, and acquire accuracy of the machine learning model trained in each of the plurality of AI devices. The processor is configured to change an execution frequency of a process relating to training of the machine learning model having an accuracy within a predetermined range.

The invention provides a model management method for artificial intelligence (AI) / machine learning (ML). The wireless communication device performs the method to perform AI / ML model monitoring and / or perform lifecycle management (LCM) on one or more AI / ML models according to an AI / ML model monitoring configuration.

A model management method and a communication device are provided. The method includes that: a node obtains a model management service provided by a model management module, the model management service supports the node to perform at least one of the following operations: storing one or more models to the model management module; updating one or more models in the model management module; and obtaining one or more models from the model management module.

The invention discloses a brain disease risk prediction method and system based on big data analysis, and belongs to the technical field of brain disease risk prediction. The method comprises the following steps: carrying out standardized preprocessing and tagged classification on brain disease related big data to generate a feature data set; mining specific disease characteristics and risk factors in the set, and carding an association rule; training a risk prediction sub-model for each disease type based on the data, and building a multi-sub-model hierarchical prediction system; and collecting to-be-predicted object data, matching a disease type, and calling the corresponding sub-model to complete risk assessment. The system comprises multiple modules for collaborative operation, and a full-process closed loop of data storage, feature processing, model management and result output is realized. According to the scheme, the pertinence, the accuracy and the efficiency of risk prediction are improved, the traceability of the whole process and the dynamic optimization of the model are realized, and reliable technical support is provided for early screening and risk early warning of brain diseases.

The subject technology provides for a model management and deployment system for machine learning models. A system includes a model manager configured to schedule execution of one or more machine learning models on one or more electronic devices or servers. The system also includes a model catalog configured to store information associated with the one or more machine learning models. The model manager may access the model catalog to determine scheduling priorities based on the stored information.

The invention relates to a full-process-oriented data asset model management method and device, equipment and a medium, and belongs to the technical field of data processing. The method comprises the following steps: sequentially performing metadata extraction, data asset directory construction and data asset access based on metadata association and directory binding on multiple data sources of a target business system, and constructing and generating a data asset full-flow chart to display a full-flow path of data asset access; predicting and supplementing missing metadata based on the double algorithms of data consanguinity logical reasoning and knowledge graph rule judgment; performing correctable multi-stage multi-round recursive quality evaluation on the data asset full-flow chart after missing metadata prediction and completion; and synchronously executing a three-layer parallel joint retrieval mechanism based on a quality evaluation result to complete joint search of multiple data assets and high-quality retrieval result display. By adopting the method, efficient and accurate management of the data asset model of the target business system can be realized.

The invention relates to an MBSE multi-field-based virtual-real fusion simulation platform and method, and the method comprises the steps: an intelligent matching module is used for receiving a to-be-detected algorithm model according to a user interface module, determining an MBSE multi-field model from a model management module, and achieving the MBSE multi-field model through the MBSE multi-field model; the virtual-real fusion test module is used for determining a plurality of test scenes constructed according to real scene data according to the MBSE multi-field model, performing full-life-cycle verification on the MBSE multi-field model and the to-be-detected algorithm model according to each test scene to obtain a corresponding verification result, and when the verification result meets a preset condition, executing the virtual-real fusion test on the to-be-detected algorithm model. The to-be-detected algorithm model is stored in the model management module, the full-life-cycle automatic verification process is achieved through the virtual-real fusion test module, the problems that virtual simulation and real object test are separated, and evaluation standards are not uniform are solved, and the method has the advantages that the test efficiency is improved, and the virtual-real fusion test capability is enhanced.

The invention discloses a metadata version control and automatic structure comparison method and system based on incremental snapshot and intelligent decision, and the method comprises the following steps: managing a metadata version through an incremental snapshot model, and enabling the incremental snapshot model to support the complete backtracking of a historical structure through storing changed incremental information and associating with a version chain; carrying out difference analysis on the metadata structure by adopting a hierarchical progressive comparison algorithm; an intelligent DDL decision engine is adopted, and an executable DDL script is generated according to the difference analysis result; in the process of generating the DDL script, metadata consanguinity information is jointly checked so as to carry out change risk assessment. Through collaborative design of all the modules, double benefits of systematic breakthrough and conventional effect enhancement are brought, and the technical effect is directly associated with collaborative design.

A wireless user equipment transmits learning model information corresponding to learning models facilitating radio functions to a network node. In response, the node transmits to the user equipment a model management indication configuration corresponding to the learning model information. The user equipment monitors learning model parameter metrics, indicative of learning model performance. Monitored metrics may be used to determine a control action, or operation, to perform, based on analysis of the metrics with respect to model performance metric criterion. A model management indication may be transmitted to the user equipment indicating a determined control action. Examples of a control operation may comprise deactivating a currently operating learning model or retraining a learning model.

The invention relates to the technical field of complex equipment data management, in particular to a model-driven complex equipment data relation automatic construction method and system. The method comprises the following steps: constructing a business entity meta-model standard framework comprising a base layer and a domain extension layer through a meta-model technology, and establishing a dual-check system; a hierarchical modeling method is adopted to construct a data model system, and model management is performed through a multi-source heterogeneous data reference mechanism and semantic version control; constructing a data association relationship by adopting a multi-modal fusion method and integrating structural analysis and semantic reasoning; and finally, four-dimensional quality evaluation of integrity, consistency, timeliness and accuracy is carried out on the data association relationship. According to the method, the problems of non-uniform data standards, low association efficiency and incomplete change transmission in complex equipment development are solved, and an automatic closed loop from data association construction to quality control is realized.

The subject technology provides for a model management and deployment system for machine learning models. A system includes a model manager configured to schedule execution of one or more machine learning models on one or more electronic devices or servers. The system also includes a model catalog configured to store information associated with the one or more machine learning models. The model manager may access the model catalog to determine scheduling priorities based on the stored information.

The invention relates to the technical field of model management, in particular to a building information model management system, which comprises a component dependency construction module for acquiring geometric and spatial information of components in a model, analyzing a supporting relationship and an attachment relationship between a bearing column and a beam, converting the components into nodes, converting the relationships into directed edges and generating a component dependency relationship graph. According to the method, the geometric and spatial information of the components in the building information model is obtained, the supporting and attaching relation between the components is analyzed, the structure of the components is converted into the node and directed edge form, graph structure expression of the dependency relation between the components is achieved, and bearing paths and mechanical connection between the components can be comprehensively reflected. Based on the structure diagram, a change propagation path is identified through recursive tracking of directed edges, all non-repeated component nodes in the path are summarized, all affected component ranges can be rapidly identified after local change is triggered, and therefore the influence range is prevented from being omitted.

The invention discloses an equipment predictive maintenance system and method based on a block chain network, and belongs to the technical field of production equipment maintenance, and the method comprises the steps: collecting equipment operation data in real time through a sensor deployed on production equipment, and transmitting the data to a block chain data storage library composed of distributed nodes after preprocessing; the storage library comprises a data acquisition node, a model management node and a maintenance execution node, and equipment operation parameters and maintenance information are isolated and stored through an independent channel; based on historical data, constructing an equipment fault model, predicting a potential fault type and probability of the equipment, and transmitting the model and a prediction result to a block chain data storage library; generating a corresponding maintenance plan according to the prediction result, and automatically distributing the maintenance plan to a maintenance execution node; and after the maintenance is completed, the log is recorded to the block chain data storage library and is bound with the original plan, so that the traceability of the whole process is ensured.

A technique for managing training data used to train a machine-learning model is disclosed. One aspect of the present disclosure relates to a model management device comprising: a data identifying unit that acquires data identifying information; a model identifying unit that, with reference to usage information of training data, identified a first machine-learning model which has been trained by using first training data identified by the data identifying information; and a processing unit that deletes the first training data from a first training data set used to train the first machine-learning model, and thereby creates a second training data set and executes processing the first machine-learning model.

The invention discloses a welding modeling management method and system, and the method comprises the steps: collecting welding data which comprises welding structure data and welding seam data, carrying out the image collection of the surface appearance of a welding seam, storing the collected data, and carrying out the modeling management of the welding seam according to the collected welding structure data. A three-dimensional model of a welding structure is created through three-dimensional modeling software, interaction is supported through a lightweight engine, welding seams are drawn in the three-dimensional model, each welding seam is endowed with an independent ID, and the welding seam state is marked through colors. According to the method, data collection of the welding seam and data collection of the welding structure are utilized, the three-dimensional model is established for the welding seam, the welding seam unification platform is suggested, and related information such as the three-dimensional model welding seam focusing real object position, the welding seam attribute, the process card and the inspection report is clicked for one-key calling, so that the cross-system retrieval cost is eliminated; modeling management of the welding seam is facilitated, so that the searching time of the welding seam is shortened, and the working efficiency is improved.

The invention discloses an MBSE model version pedigree iteration method and system based on a graph theory and a knowledge graph. The method comprises the following steps: constructing an MBSE model of an aerospace craft and mapping the MBSE model into an attribute graph; a directed acyclic graph is adopted to record a version iteration process, management is carried out through a version number system comprising a main version number, a combined version number and a revised version number, and a differential storage strategy is adopted; and performing change detection and merging based on a baseline, accurately identifying changes through a model comparison algorithm including internal attributes, internal relationships, overall relationships and difference analysis, and processing conflicts in collaborative design. According to the method, atomic-scale version control is realized, the problems of missing change traceability, low verification efficiency and multi-baseline conflict are solved, and the efficiency and quality of aerospace craft full-life-cycle model management are improved.

The invention discloses an intelligent early warning method and system based on laser control industrial data, and belongs to the technical field of laser safety early warning. The system comprises an equipment control module, a data acquisition module, an analysis database, a model management module, a monitoring judgment module and an alarm module, the equipment control module is used for controlling the laser to cut the industrial product; the data acquisition module is used for acquiring cutting data and parameter data generated in the industrial product cutting process; the analysis database is used for storing historical data of the cutting data and the parameter data; the model management module is used for establishing a deviation analysis model and analyzing the influence of different influence parameters on the cutting deviation of the industrial product; the monitoring judgment module is used for judging whether current industrial product cutting is abnormal or not; the alarm module is used for carrying out abnormity alarm; according to the method, the influence of different influence parameters on the cutting deviation of the industrial product is considered, and the accuracy of system data analysis is improved.

This disclosure relates to the collection of data for the management and monitoring of AI / ML models. In one described embodiment, a method performed by user equipment (UE) includes receiving from a network node a first instruction for model management decisions and a second instruction for model performance reporting, and, if the first instruction does not indicate model activation and the second instruction enables model performance reporting, running the model and reporting model performance to the network node without using the output from the model to control communication with the network node. Various other methods, including corresponding network node methods, are disclosed.

The invention relates to the technical field of AI model management, in particular to a mine AI model fine adjustment and optimization management method based on incremental learning, which comprises the following steps: calling a current version model and a previous version model for each heading machine state data sample in an incremental data stream, calculating the KL divergence of the output distribution of the two models, and calculating the KL divergence of the output distribution of the two models; and meanwhile, the prediction entropy of the current version model on the heading machine state data sample is calculated. According to the method, the KL divergence and the prediction entropy in the heading machine state data sample are subjected to two-dimensional calculation, and the sample is mapped to the two-dimensional space to identify the Pareto frontier set, so that screening of high-potential samples with coexistence of information value and model uncertainty can be realized, invalid training of redundant samples is avoided, the data utilization rate is improved, and the method is suitable for large-scale popularization and application. And an incremental training key sample set is uniformly constructed after the set boundary samples are manually labeled, so that a high-quality information source can be continuously introduced in model updating, and targeted convergence of a training target is realized.

The invention provides a large model management software and hardware integrated device and a management method. The large model management software and hardware integrated device comprises a heterogeneous computing unit, a computing power processor integrating multiple architectures and a storage device. The framework scheduling unit is deployed on the heterogeneous computing unit, dynamically allocates computing power based on physical resources of the heterogeneous computing unit and adapts to an AI framework; the model full-period management unit is used for directly calling the execution capability of the framework scheduling unit and completing model training, parameter storage and reasoning service packaging; the application construction unit is connected with the reasoning service of the model full-period management unit through a standardized interface and provides knowledge enhancement, agent cooperation and application arrangement capabilities; and the optimization decision-making unit is used for collecting operation data of the heterogeneous calculation unit and the model full-period management unit in real time, dynamically generating a resource configuration strategy and feeding back the resource configuration strategy to the framework scheduling unit to form closed-loop control.

The invention provides a railway BIM modeling method based on a cloud architecture. The railway BIM modeling method comprises the following steps: collecting design data of related equipment related to a railway; making a railway BIM model based on three-dimensional design software; creating a three-dimensional scene of the railway engineering, performing cache slicing through a cloud end, and publishing the three-dimensional scene as a three-dimensional data service; building a cloud architecture GIS environment; analyzing the BIM models in batches in the cloud architecture GIS environment, and storing the BIM models in a distributed system; a railway BIM model management platform based on the cloud GIS is built, railway BIM model data service is released, and visual display and automatic integration of the BIM model are achieved. And the cloud architecture and BIM modeling are combined, so that the modeling efficiency is effectively improved.