732 results about "Model management" patented technology

An advanced model management platform for optimizing and securing generative artificial intelligence systems such as large language models (LLMs) and diffusion models. The platform incorporates various techniques to address the limitations of current generative AI systems, such as hallucination, lack of validation, security vulnerabilities, and inadequate model management. The system employs reinforcement learning algorithms for model optimization, retrieval augmented generation (RAG) for hallucination mitigation, domain-specific validation against expert knowledge, model distillation and similarity scoring for security, adversarial training for robustness, and attention mechanism search and model blending for advanced management and neuro symbolic AI routine combinations. By integrating these techniques, the platform significantly improves the performance, reliability, and security of generative AI across a wide range of tasks and domains leveraging the best elements of symbolic and connectionist techniques alongside automated planning and modeling simulation.

The invention relates to the technical field of intelligent questions and answers, and discloses a commercial real estate digital assistant system based on a large model and an intelligent agent, and the system comprises an original data obtaining module which is used for obtaining the original data of a commercial real estate; the data processing and knowledge base construction module is used for processing the original data to construct different types of knowledge bases; the data and tool application module is used for querying a corresponding knowledge base or calling a tool according to the target question, generating an answer and displaying the answer; the task disassembling and process execution module is used for disassembling the target problem into a plurality of task processes, generating an execution link, and combining the task processes and the execution link to execute the task; a domain large model training module; and a field large model management module. According to related application scenes and industry knowledge in the commercial real estate field, the large model in the training field is finely adjusted, the large model and the agent technology are combined, the digital assistant system oriented to the commercial real estate field is constructed, and complex tasks and requirements in the commercial real estate field are better coped with.

A system for automatically self-labeling a digital dataset includes a first sensor for generating a first data stream, a second sensor for collecting information to generate a second data stream, and a causal model manager (CMM). The CMM is configured to determine a first causal event from a first data segment of the first data stream, and a causal relation between the first causal event and a second data segment selected from the second data stream. The system further includes (a) an interactive time model for determining an interaction time between the first and second data segments, and (b) a self-labeling subsystem configured to derive a label from the second data segment, associate the first data segment with the derived label, form a self-labeled data pair from the associated first data segment and the derived label, and automatically annotate the self-labeled data pair with the interaction time.

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 invention discloses a large model scheduling system and method, a server, a medium and a product. The large model scheduling system comprises a model management module, a computing power scheduling module and a model scheduling module, the model management module is used for performing corresponding model management on a target large model in response to a management operation of the client for the target large model; the computing power scheduling module is used for determining a target computing power resource node matched with the large model according to model parameter information of the large model for each large model, and mounting the large model to a container on the target computing power resource node; and the model scheduling module is used for acquiring the container parameter information of each container, and performing model scheduling processing on the large model mounted on the abnormal container when the container parameter information is abnormal. According to the technical scheme, the computing power resource utilization rate is improved, and efficient computing power resource selection and large model scheduling are achieved.

The invention belongs to the technical field of artificial intelligence model management, and discloses a multi-scene multi-base large model engine system. Comprising a front-end interaction layer, a service function layer, a core technology layer and a bottom supporting layer, the front-end interaction layer is used for providing an access mode, an interface protocol, authority management and log recording; the business function layer is used for meeting core business requirements of multiple scenes in the financial industry; the core technology layer comprises a multi-task instruction fine tuning platform, a large model automatic evaluation platform and a large model management platform; according to the method, the optimal model is dynamically matched, the task is efficiently executed, and through the multi-task instruction fine adjustment platform and the automatic evaluation platform, the model performance can be continuously optimized, the efficient utilization of model resources is realized, and meanwhile, the accuracy and response efficiency of service processing are improved.

The invention discloses a building construction scheme multi-model management system and method, and belongs to the technical field of building construction management. The system is composed of four subsystems based on a building construction scheme natural language processing model: a construction industry multi-modal professional knowledge question-answering system, a construction industry professional document compiling system, a construction industry multi-modal retrieval system and a construction scheme content auditing system. The construction industry professional document compilation system adopts a multi-mode diffusion large model technology, so that the built construction image generation system can intelligently respond to a text demand input by a user, automatically generate a building construction image matched with the text demand, or perform style conversion on a building image uploaded by the user, and automatically generate a construction image matched with the text demand. According to the method, the building images meeting specific requirements are created, instant building construction reference drawings are provided for users, the workload of the users in the drawing process is greatly reduced through the one-key image generation function, and the working efficiency in the building construction scheme writing stage is remarkably improved.

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.

A computer-implemented system, computer-implemented method, and computer-program product includes receiving, via a graphical user interface, a request to generate an initial design of experiment plan based on one or more experiment factors; generating a first plan settings container object that represents the initial design of experiment plan in computer memory; and instantiating, within the graphical user interface, a plan explorer section that includes a plan settings graphical entry that displays a graphical representation of a plan factors data object and a plan model data object associated with the first plan settings container object.

The invention discloses a tumor whole course intelligent management platform and method, and particularly relates to the technical field of medical model management. Carrying out semantic analysis and uniform format processing on the multi-modal data from different sources by utilizing a natural language processing technology and a standardized tool; using a feature selection algorithm to screen key features related to tumor types and treatment schemes; through analyzing mutual information of the key features and the target variables and mutual information among the key features, evaluating the degree of redundant hidden dangers existing in the screened key features; the semantic consistency of the multi-modal data from different sources is evaluated by comparing and analyzing the prediction label and the actual label of the multi-modal data; and comprehensively analyzing the redundant hidden danger degree of the screened key features and the semantic consistency of the multi-modal data from different sources, and judging whether the personalized treatment effect prediction model can be constructed or not.

The invention provides a model management system and a business processing method, and relates to the technical field of computers. The model management system comprises a model adaptation module and a model fusion module, and the model adaptation module is used for matching at least one target large language model suitable for to-be-processed text data in multiple types of large language models of current application according to the to-be-processed text data; based on the to-be-processed text data, calling at least one target large language model through a unified API interface to obtain an output result obtained by processing the to-be-processed text data by applying the target large language model; and the fusion module is used for carrying out fusion processing on the output result to obtain a processing result corresponding to the to-be-processed text data. Dynamic replacement of the large language model is achieved through the model adaptation module, and the complexity and cost of large language model replacement are reduced. The output of the multiple large language models is fused through the fusion module, the advantages of the large language models are fully utilized, and the processing capacity and precision of the system are improved.

In example implementations described herein, there are systems and methods for generating recommendations for a first user regarding at least one of an industrial process or an industrial product including receiving information from one or more input sources associated with at least one of the industrial process or the industrial product, processing the received information using one or more MT models associated with a model management system, generating, for the first user, a first natural language query regarding at least one of the received information or the processed information using one or more MT NLP models, generating, for the first user, a first natural language recommendation based on the first natural language query and at least one of the received information or the processed information, and outputting, for the first user, a first indication of at least the first natural language recommendation via the user interface.

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 multi-type central air conditioner integrated optimization automatic control system, which relates to the technical field of air conditioner control, and comprises an equipment dynamic modeling module, an MPC optimization control module, a dynamic reference and diagnosis module, an RL driving MPC setting module, a dynamic sliding window processing module and a large model management module, the dynamic sliding window processing module gathers and performs continuous cutting and context association processing on information streams from the modules to generate serialized information fragments adaptive to the input length of the large model management module, and the large model management module serves as a core cognition and decision center; and performing deep fusion analysis on the received serialized information fragments by using an internal attention mechanism to realize advanced operation strategy generation and deep fault reason tracing, and providing decision support and system state interpretation through a natural language interaction interface. And finally, comprehensive cognition, predictive insight and self-adaptive evolutionary management of the global state of the central air conditioning system are achieved.

The invention discloses a method for dynamically calling multiple models for a deep learning algorithm and a service architecture. The method comprises the steps that a client sends a request to a scheduling service through a standard AP I interface; after the scheduling service receives the request, key information of the request is analyzed and extracted to generate a task queue, and a Server server is selected; the scheduling service acquires state data provided by the Agent service in real time, and performs task allocation according to the load condition of the Server; the scheduling service stores the selected task information into a database, and marks a'to-be-processed 'state in a task state table; after receiving the scheduling task, the Server calls a model management service to load a specified reasoning model; and S6, after the reasoning task is executed, the reasoning service pool informs a scheduling service of a result through a callback mechanism. The method has the advantages that the processing capacity and efficiency of the deep learning task are improved, the requirements of different tasks are met by dynamically calling multiple models, meanwhile, resource use is optimized, and the expandability of the system is guaranteed.

Embodiments include methods for a first network node or function (NNF) configured for machine learning (ML) model management in a communication network. Such methods include receiving, from a second NNF of the communication network, a first message including: one or more ML model identifiers corresponding to one or more ML models maintained by the first node, or an identifier of an analytic based on the ML model(s). Such methods include sending, to the second NNF, a second message including one of the following: a plurality of tuples corresponding to a plurality of ML models on which the analytic is based, each tuple including a different ML model identifier and information element(s) associated with the corresponding ML model; or a single tuple including the analytic identifier and information element(s) associated with a single ML model on which the analytic is based. Other embodiments include complementary methods for the second NNF.

The invention discloses a Web application firewall security defense method and system, and belongs to the technical field of network security, and the method specifically comprises the steps: collecting and preprocessing network flow data in real time, constructing standardized data input, and training a multi-modal deep neural network attack detection model to recognize attack behaviors in a network; in the real-time detection process, the model outputs an attack type and a probability, and when an attack is detected, the firewall automatically generates an attack behavior graph, triggers a multi-level depth defense mechanism and feeds back a result to the model management module; and the model management module updates model parameters in real time through online learning, realizes version management, and performs model optimization in combination with a rapid rollback mode, thereby improving the network security protection capability.

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.

The invention discloses a project progress, quality and safety collaborative management and control system and method based on BIM and Internet of Things, and belongs to the technical field of constructional engineering informatization management. In order to improve engineering management efficiency and reliability, the system comprises a data acquisition layer, a data processing layer, an application layer and a security module. The data acquisition layer is connected with the data processing layer, the data processing layer is connected with the application layer, and the security module is respectively connected with the data acquisition layer, the data processing layer and the application layer; the data acquisition layer comprises IoT equipment, an external data interface, data middleware and a BIM model, the IoT equipment acquires data through the external data interface, the IoT equipment is connected with the BIM model through the data middleware, and the data processing layer comprises a multi-source data fusion engine and an intelligent algorithm module; the application layer comprises a model management module, a model display module, an early warning management module, a data management module, a three-dimensional visual monitoring platform, an intelligent decision center and a mobile terminal module. The project management efficiency is improved.

The invention discloses a three-dimensional BIM (Building Information Modeling) and GIS (Geographic Information System) model-based integrated city district-level data management platform and method, and the platform forms a three-dimensional information integrated data management platform, collects geographic information data and basic data through an information data collection module, and converts the geographic information data and basic data into a BIM model file; the BIM model building module is used for making a BIM model based on three-dimensional software; the GIS model building module is used for building a GIS model and integrating a development environment and a database environment at the same time; the BIM model lightweight processing module is used for optimizing the BIM model and performing lightweight processing on the BIM model; the platform management module is used for constructing a BIM model management platform based on the cloud GIS, the BIM model management platform based on the cloud GIS is constructed in combination with the cloud GIS technology, visual display and automatic integration of the BIM model can be carried out, and centralized collection and analysis of more related data are achieved.

The invention provides an efficient AI model management and safe loading system and method oriented to a Serverless framework, and aims to solve the high concurrency performance bottleneck and potential safety hazards of AI model loading in a Serverless environment. According to the system, an AI model management module is introduced, efficient semantic cutting is carried out on an uploaded AI model, and fine-grained encryption model blocks are generated; a high-performance P2P network is constructed by utilizing a Serverless cluster, and distributed storage and fast routing of model blocks are realized; a function instance loads a model block in a high-concurrency mode through a P2P network, a multi-stage intelligent cache is constructed locally, and dynamic caching and prefetching are achieved. According to the method, the model loading parallelism degree is improved by adopting a heuristic cutting algorithm, lightweight model updating is realized by utilizing incremental updating transactions, and the loading overhead is minimized. According to the method, the AI model loading performance and efficiency in the Serverless scene are effectively improved, meanwhile, the flexibility and safety of model management are considered, and the method has remarkable technical innovation and practical value.

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.

Provided in the present disclosure is a building model management method. The method comprises: acquiring standardized model information of a target building design model, wherein the target building design model comprises at least one target three-dimensional component, and the standardized model information comprises a standardized component graph of each target three-dimensional component; acquiring a real-scene point cloud model, in a point cloud space, of the current building on a construction site; by means of a preset coordinate conversion matrix, mapping the standardized component graph of each target three-dimensional component to the point cloud space, so as to obtain a component point cloud model corresponding to each target three-dimensional component; and respectively calculating the degrees of coincidence between the component point cloud models of at least some of the target three-dimensional components and the real-scene point cloud model, and using the degree-of-coincidence calculation result as the actual construction progress of the corresponding target three-dimensional component at the current moment.

The invention discloses a signal timing scheme automatic generation system based on multiple algorithms, and the system comprises an index data statistics module which is used for carrying out the statistics of a plurality of preset index data in obtained traffic big data in any traffic region which is delimited in advance, and obtaining a statistical result of the index data; the index algorithm model management module is used for performing result representation on any index in the statistical result by using a corresponding specific index algorithm model; the optimization model generation module is used for constructing a multi-algorithm signal timing optimization model for a plurality of index algorithm models corresponding to the plurality of indexes; and the problem solving module is used for solving the optimization model and generating a signal timing scheme of the target traffic area according to a solving result. According to the invention, through integration of the multi-algorithm model, automatic generation of the traffic signal timing scheme is realized, the efficiency and effect of traffic management are improved, and powerful technical support is provided for sustainable development of urban traffic.

A model management system provides a centralized repository for storing and accessing models. The model management system receives an input to store a model object in a first model state generated based on a first set of known variables. The model management system generates a first file including a first set of functions defining the first model state and associates the first file with a model key identifying the model object. The model management system receives an input to store the model object in a second model state having been generated based on the first model state and a second set of known variables. The model management system generates a second file including a second set of functions defining the second model state and associates the second file with the model key. The model management system identifies available versions of the model object based on the model key.

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.

Certain aspects of the present disclosure provide method of wireless communications by a user equipment (UE), generally including obtaining, from a network entity, a performance report for a machine learning (ML) model running on at least one of the UE or a network entity and participating in a change to the ML model based on the performance report.

The invention discloses a visual recognition algorithm polymorphic model microtechnology based on edge cloud and an application system thereof, and belongs to the technical field of computer vision, the visual recognition algorithm polymorphic model microtechnology comprises a cloud end and an edge end, the cloud end comprises a polymorphic model management module and a model optimization module, the edge end comprises a preprocessing module, and the polymorphic model management module is connected with the model optimization module. Comprising n related visual identification models, an optimal model is automatically matched for a current task through an intelligent decision-making mechanism based on calculation precision, complexity and load of different visual identification models, and the model optimization module collects visual identification model samples in use. According to the visual identification algorithm polymorphic model microtechnology based on the edge cloud and the application system thereof, model management, model screening, model optimization and resource optimization can be realized, the response speed and the resource utilization efficiency of a visual identification system are remarkably improved, and the visual identification algorithm polymorphic model microtechnology is suitable for various application scenes with high requirements on real-time performance, accuracy and safety.

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 provides a communication method and device, and relates to the technical field of communication. In the method, after the model application equipment indicates the first state of one or more first models to the model management equipment, the first state can be maintained in the first time window, so that the condition that the model application equipment frequently reports the first state of one or more first models to the model management equipment is avoided; and information interaction between the model application equipment and the model management equipment is reduced.