736results about "Computer simulations" patented technology

A method, an apparatus, and a computer readable medium for storing instructions are described for a user terminal and a base station for updating an AI / ML configuration in case of a handover. The method performed by a user equipment comprising operating a first AI / ML configuration in a coverage area of a first base station; receiving an AI / ML configuration information indicating a second AI / ML configuration; operating the second AI / ML configuration indicated by the AI / ML configuration information in the coverage area of a second base station. Operating a first AI / ML configuration comprises operating a first AI / ML Model or a first AI / ML Model with a first AI / ML Model configuration in the coverage area of the first base station. The first AI / ML Model is associated with a first AI / ML Model identifier and the first AI / ML Model configuration is associated with a first AI / ML Model configuration identifier. Operating the second AI / ML configuration comprises operating a second AI / ML Model or the first AI / ML Model with a second configuration in the coverage area of the second base station. The second AI / ML Model is associated with a second AI / ML Model identifier and the second AI / ML Model configuration is associated with a second AI / ML Model configuration identifier. Indicating the second AI / ML configuration comprises indicating a second AI / ML Model identifier and / or a second AI / ML Model configuration identifier.

The invention relates to the technical field of parameter optimization, in particular to an automatic kernel network parameter optimization method, which comprises the steps of constructing an enhanced deep Q network model, and integrating the enhanced deep Q network model with a priority playback buffer area, a meta learning module, a Bayesian optimizer and a neural architecture search module; using performance index data to train an enhanced deep Q network model, the training process including using a priority playback buffer to store and sample empirical data, using a meta-learning module to perform task adaptation, and monitoring training indexes of multiple dimensions to evaluate the convergence state of the model; selecting a kernel parameter adjustment action according to the current state through the trained enhanced deep Q network model; executing the selected kernel parameter adjustment action, and evaluating a parameter adjustment effect based on the multi-target reward function; and updating the enhanced deep Q network model according to an evaluation result, wherein the priority playback buffer area and the Bayesian optimizer are utilized in the updating process.

The invention provides a large-model-oriented heterogeneous computing power adaptive compiling method, which comprises the following steps that: a user inputs a trained large model through a system interface, and a system front-end conversion module analyzes a computational graph of the model and converts the computational graph into an intermediate representation based on a unified operator description language (UDL); the system hardware sensing module automatically detects and extracts hardware feature fingerprints of at least one piece of target hardware; based on the unified operator description language UDL intermediate representation and the hardware feature fingerprint, automatically generating an optimization adaptation rule oriented to at least one piece of target hardware; wherein the basis of parameterized filling comprises specific parameters of hardware feature fingerprints and optimized attribute tags carried in an intermediate representation of a unified operator description language (UDL); and generating and deploying multiple back-end codes. The method has the beneficial effects that intelligent compiling based on hardware features can be realized, and the deployment efficiency and the operation performance of a large model in a complex heterogeneous computing power cluster are remarkably improved.

The invention relates to a method for deploying a spiking neural network to a hardware device. The method includes providing the spiking neural network, training the spiking neural network to obtain a trained spiking neural network, mapping neurons and synapses in the trained spiking neural network to corresponding components of the hardware device, simulating deployment of the trained spiking neural network on a hardware device using the obtained mapping, and deploying the trained spiking neural network to the hardware device using the mapping and the simulation. The training, mapping, simulation and deployment steps are executed by using hardware information of the hardware device; wherein the hardware information comprises at least one of hardware resource constraints, hardware connection constraints, dynamic range of hardware design parameters, characterization or statistics of neurons and synapses, reconfigurability, programmability, yield, computing resources, temporal characteristics, constraints on pre-processing, interfaces and peripheral devices, and available encoders and / or decoders.

The invention relates to the technical field of converters, in particular to an LLC perception type physical information nested neural network parameter estimation method suitable for an LLC resonant converter, and the method comprises the following steps: S1, constructing a continuous time state space model of the LLC resonant converter, and carrying out the discretization processing; s2, an LLC perception type physical information nested neural network is constructed, and the LLC perception type physical information nested neural network comprises a data reconstruction network and a physical information nested neural network which are connected and is used for online parameter identification of the LLC resonant converter; the data reconstruction network comprises a resonance state judgment layer, a K2 operation layer, a pseudo label generation layer, a constraint layer and a data reconstruction layer; the physical information nested neural network comprises a middle state mapping layer and a physical layer; defining LLC perception type physical information nested neural network input; s3, constructing a loss function; and S4, deploying and executing the LLC perception type physical information nested neural network model.

The invention provides a medical physical examination data intelligent processing and large model offline deployment method and system. The method comprises the following steps: performing online configuration in an offline deployment basic environment, deploying a physical examination data processing algorithm module, downloading a pre-training large model file and a reasoning framework from a model warehouse, and generating a distributable mirror image through a packaging command; performing offline deployment on the distributable mirror image, transmitting the mirror image to a server without an external network through a physical medium, importing and loading the mirror image, and starting a container service; cleaning and standardizing the received physical examination data, matching the standardized data with a medical data matching library, and calculating the severity level; and preprocessing the unstructured medical text, calling an off-line deployed large model to perform semantic analysis and generate an explanatory suggestion, and integrating processing results to generate a standardized physical examination report. According to the invention, off-line deployment and application of a large model in an external network-free environment are realized, and the intelligent level and efficiency of physical examination data processing are improved.

The invention relates to the technical field of image recognition, in particular to a building plane element recognition model construction method based on a convolutional neural network, and the method comprises the following steps: obtaining an input APN sample; elements in the APN sample are labeled, and a labeled file is generated; converting the annotation file into a format required by YOLO, and normalizing the annotation file; performing data enhancement on the APN sample, expanding the training data volume, and outputting to obtain an element detection result and a feature vector; installing dependency and carrying out data configuration; setting command line model parameters and customizing training scripts; and carrying out model training and model reasoning. According to the method, the plane layout is abstracted based on the machine learning method, and the vector data type has high flexibility and deformation capability, so that the vector output which keeps the original plane image form unchanged can be converted into various objects according to the purpose of a user. And classifying and identifying the plane elements by using the GNN.

Apparatuses, systems, and techniques to assign a processing resource to an inference request directed to a neural network based on an amount of information to be inferenced indicated by said request. In at least one embodiment, an AI application is deployed with a software wrapper that intercepts inference requests and dynamically distributes such requests among available processing resources such as host processor(s) and / or AI accelerator(s) to improve execution performance of said AI application.

The invention discloses a mobile terminal real-time action monitoring method and system. The method belongs to the technical field of neural network target monitoring. The problem that the application effect of an existing mobile terminal motion monitoring model in real-time scenes such as monitoring APP and AR interaction is seriously restricted due to the fact that the existing mobile terminal motion monitoring model is difficult to balance the monitoring precision, the model size and the reasoning speed is solved. A complete data set construction process of data collection, frame extraction, standardized preprocessing, multi-dimensional enhancement and double-input construction is provided, and the generalization ability of the model is remarkably improved; a 3D convolution and ResNet fused lightweight model is designed, the action spatial-temporal feature capture capability and the mobile terminal deployment requirement are considered, and the model parameter scale is only 60% of that of a traditional 3D CNN model; through double-input data construction and a result optimization mechanism, the monitoring accuracy of the model in a real scene is not lower than 84%, and the actual application requirement is met.

The system according to this embodiment aims to seamlessly switch between dialogue histories between different generative AIs. [Solution] The system according to the embodiment comprises an export unit, an import unit, and a switching unit. The export unit exports the dialogue history. The import unit imports the dialogue history exported by the export unit. The switching unit seamlessly switches between different generative AIs based on the dialogue history imported by the import unit.

A generative AI framework for an enterprise may utilize a cloud-based generative AI operational environment to execute LLMs. A mini-platform library data store contains electronic records associated with a plurality of potential generative AI mini-platforms, and a workflow function library data store contains functions usable to customize managed workflows. A plurality of active enterprise mini-platforms may each be based on a potential generative AI mini-platform and have a customized managed workflow for an enterprise use case. An enterprise application integration component coupled to the cloud-based generative AI operational environment and the active enterprise mini-platforms facilitates model routing and orchestration to support the LLMs. The integration component may also interface between the cloud-based generative AI operational environment and the active enterprise mini-platforms to provide access to enterprise data that is processed via customized managed workflows.

A compiler of a computing device is described that identifies a sequence of neural network models frequently invoked by an application of the computing device, compiles the models in that sequence, and loads a static random access memory (SRAM) of a hardware accelerator with the compiled models only when the same compiled models—from another, but same, sequence that was previously invoked—are not already present in the SRAM. This prevents unnecessary reloading of compiled models into the SRAM, thereby increasing runtime speed and conserving computational energy.

Integrated cells may perform matrix multiplication (MatMul) operations. An integrated cell may include a random-access memory (RAM) cell, dot product unit(s), multiplexer(s), adder, route-in unit, control unit, and vector machine. The RAM cell may store weights and activations. The dot product unit(s) may compute dot products from the weights and activations. The adder may accumulate the dot products. The route-in unit may facilitate data transfer from the RAM cell to the dot product unit(s) or data transfer from another integrated cell to the integrated cell. The control unit may manage memory operations and detect and repair errors in memory operations. The vector machine may provide instructions to the dot product unit(s) and multiplexers to direct the flow of multiply-accumulate operations. Counters may be used to control weight fetching from RAM cells. A MatMul operation may be decomposed, and the integrated cells may perform the MatMul operation through multiple clock cycles.

A method and device for estimating physical property parameters are disclosed. The method of estimating physical property parameters for a drape simulation of a virtual fabric includes generating a mesh by applying physical property parameters corresponding to the virtual fabric to a neural network, obtaining, based on the mesh, drape data corresponding to a type of target data related to a drape of the virtual fabric, and updating the physical property parameters based on an error between the obtained drape data and the target data.

The invention belongs to the technical field of software development, and particularly provides a research and development-oriented long and short-term memory framework construction method and system, which adopts a layered memory architecture to construct four core modules including a short-term memory compressor, a medium-term memory aggregator, a long-term memory graph and a cross-layer memory router. The system takes multi-source input such as research and development dialogues, code snippets and project documents as a starting point, extracts research and development elements through semantic analysis and entity recognition technologies, compresses lengthy dialogues into structured short-term memory by utilizing an attention distillation mechanism, upgrades high-frequency short-term memory into medium-term knowledge fragments based on a time sequence attenuation algorithm, and improves the research and development efficiency. And constructing a long-term knowledge graph containing developer portraits, project dependence and normative standards by adopting a graph convolutional network. Context understanding accuracy, multi-round dialogue continuity and personalized service quality of a large model in a research and development scene are remarkably improved, and the method is suitable for mainstream research and development tool scenes such as IDE plug-ins, code review and architecture design.

The invention relates to the field of artificial intelligence, and provides a hardware-aware ONNX graph optimization method and a hardware-aware graph optimization and compilation engine, which break through the barrier between hardware-independent optimization and hardware-related compilation, and improve the optimization efficiency through a unified and closed-loop optimization framework. An original ONNX model calculation graph is optimized and compiled based on hardware characteristics of an AI chip, deep collaborative optimization from the ONNX calculation graph to AI chip codes is achieved, and therefore the performance of the AI chip is played to the maximum extent.

Presented herein are systems and methods that provide for automated analysis of three-dimensional (3D) medical images of a subject in order to automatically identify specific 3D volumes within the 3D images that correspond to specific organs and / or tissue. In certain embodiments, the accurate identification of one or more such volumes can be used to determine quantitative metrics that measure uptake of radiopharmaceuticals in particular organs and / or tissue regions. These uptake metrics can be used to assess disease state in a subject, determine a prognosis for a subject, and / or determine efficacy of a treatment modality.

Embodiments described herein provide an AI guardrail system that integrates an agentic compliance evaluation framework with an agentic governance ontology framework to automate AI risk assessment and management. For the compliance evaluation framework, embodiments provide a Digital Risk and Compliance Officer (DRCO) agent built upon an LLM to verify AI compliance in an AI system based on a knowledge base managed by an AI governance ontology. For the governance ontology framework, embodiments provide an AI Governance Ontology (GO) agent built upon two LLMs that generate and update a knowledge base representing concepts, relationships, and metadata related to the governance of AI systems based on AI system generated conversation transcripts.

This application describes, amongst other things, methods and systems for building and deploying agents. An example method includes obtaining orchestration data about a set of task-specific components, where each respective task-specific components in the set of task-specific components is configured to assist with a respective task of a plurality of tasks. The method also includes receiving a prompt related to one or more tasks of the plurality of tasks and selecting a subset of task-specific components based on the prompt and the orchestration data. The method further includes coordinating, via a routing agent, interactions between the task-specific components, including providing data related to the prompt to the task-specific components and receiving responses from the task-specific components, and generating a complete response to the prompt that addresses the one or more tasks using the responses from the task-specific components.

A method for compiling a computational graph, and a related product. The method comprises: acquiring a computational graph to be compiled that is expressed by a second intermediate representation, performing forward inference of a shape, and on the basis of the forward inference and tensor data splitting information, obtaining complete shape information; using the complete shape information to determine whether the tensor data splitting information needs to be adjusted; on the basis of a determination result, determining the tensor data splitting information that meets requirements; on the basis of the tensor data splitting information that meets the requirements, performing memory access pattern derivation on operators in the computational graph; on the basis of a derived memory access pattern, determining address-domain-related parameters of instructions involved in loops in code logic of the computational graph; performing pipeline scheduling on the instructions in the loops; and on the basis of the address-domain-related parameters of the instructions involved in the loops and a pipeline scheduling result of the instructions, compiling the computational graph, so as to obtain a binary file recognizable by an intelligent processor.

Techniques for building and maintaining model webs are described. In some examples, a model web is built by selecting models for the model web from one or more available model types based on at least one or more of availability, tensor information, and compute type, instantiating synapses between the selected models to form the model web and updating information regarding availability of the selected models of the model web to indicate being in use.

A framework for easy development of a machine learning solution is provided. The framework includes connecting data sources at all scale levels from a user; assessing data schema, data risk, and data quality status; performing scalable feature engineering and transformation; and automating machine learning model optimization. The framework also includes functionalities for generating production code and automatic model documentation.

Systems and methods described herein relate to a generative artificial intelligence (AI) access layer that is implemented for dynamic control of a software application. Input is received from the software application. A generative AI model is used to detect a relevant capability based on the input. Prompt data is generated based on generative AI scenario settings for the relevant capability. The prompt data includes at least some of the input and context data accessible to the software application. A capability result is generated by using the generative AI model to process the prompt data. The generation of the capability result is dynamically controlled using the generative AI scenario settings. The software application executes the relevant capability based on the capability result. Output is presented within a user interface of the software application.

A system for compiling a machine learning network for execution on a plurality of interconnected processing elements performs the following. It selects splits (Ps,Qs,Ks) for individual layers of the machine learning network based on (a) costs of data transfer between processing elements assuming that inputs and outputs of individual layers have a same spatial split (Ps,Qs), and (b) costs of data transfer between processing elements resulting from differences in the spatial splits for inputs and outputs of individual layers. In addition, it selects the same splits (Ps,Qs,Ks) for layers that have the same spatial size P×Q. It then generates a computer program that allocates computations for executing the machine learning network to the processing elements according to the selected splits for the individual layers.

The invention relates to early exit of a natural language processing model. The present disclosure provides a natural language processing (NLP) model arranged to run in two dictionaries, one being a subset of the other. The NLP model may be arranged to generate an output based on the subset dictionary and to exit processing of the NLP model to potentially save computational cycles.

The system according to the embodiment aims to generate appropriate recipes taking into consideration the health information, allergy information, and refrigerator inventory information of family members. [Solution] A system according to an embodiment includes an input unit, an acquisition unit, a generation unit, and a provision unit. The input unit inputs health information or allergy information of family members and dietary needs. The acquisition unit acquires refrigerator inventory information. The generation unit generates a recipe based on the information obtained by the input unit and the acquisition unit. The provision unit provides the recipe generated by the generation unit.

This invention discloses an intelligent identification and early warning system for unsafe behaviors of construction workers, belonging to the field of construction site safety technology. It includes a multimodal perception layer, a data preprocessing layer, a cross-modal spatiotemporal attention fusion layer, an unsafe behavior identification and prediction layer, a hierarchical early warning and response layer, and an edge-cloud collaborative computing layer. The cross-modal spatiotemporal attention fusion layer is communicatively connected to the data preprocessing layer to extract features from different modalities and dynamically fuses multimodal features through a cross-modal spatiotemporal attention mechanism. It adopts a three-dimensional multimodal perception architecture integrating physiology, behavior, and environment, fusing data from multiple sensors to fully utilize the complementarity of different modalities. In particular, the proposed cross-modal spatiotemporal attention fusion network can dynamically learn the importance weights of different modalities at different spatiotemporal locations, effectively solving the problem of feature extraction failure in complex construction site environments.

To provide an information processor for supporting the generation of a sentence using a language model.SOLUTION: The above problem is solved by an information processing device including chatbot control means for asking one or more questions to an end user according to a scenario and acquiring an answer to the question, prompt generation means for generating a prompt in which one or more variable portions included in a template prompt are replaced with an answer corresponding to the variable portion, and sentence data acquisition means for acquiring sentence data generated by inputting the generated prompt to a language model, in which the chatbot control means displays the acquired sentence data on a user terminal operated by the end user.SELECTED DRAWING: Figure 3

A method for dynamic quantization of a model includes: accessing a floating-point output activation of an operation and characterized by a tensor including a set of floating-point elements; and segmenting the tensor into a set of subtensors, each subtensor characterized by a quantity of elements corresponding to a group size assigned to the operation and including a subset of floating-point elements. The method also includes, for each subtensor: calculating a dynamic range of the subset of floating-point elements; calculating a local scale for the subset of floating-point elements based on the dynamic range; and converting the subset of floating-point elements into a subset of reduced- precision elements, in a first set of reduced-precision elements, characterized by the local scale. The method further includes: generating a reduced-precision output activation characterized by the first set of reduced-precision elements.