1250 results about "Model inference" patented technology

Disclosed in the present invention are an aviation equipment reliability evaluation method and system based on a knowledge graph and model inference. The method comprises: acquiring data of human factors, equipment systems, and a working environment of aviation equipment; carrying out preprocessing and text labeling on the acquired data; inputting the labeled text information into a constructed entity relationship joint extraction model to form a high-quality structured triple of the knowledge graph; constructing an elastic knowledge graph for the aviation equipment, wherein the elastic knowledge graph comprises an online knowledge graph and an offline knowledge graph which has aviation equipment reliability; and extracting semantic features, and analyzing the similarity between the extracted features to realize indirect inference of the aviation equipment reliability. The present invention fully fuses expert experience and knowledge data, and exerts respective advantages of a human brain and machine intelligence, so as to achieve accurate analysis and prediction of aviation equipment reliability, thereby providing intelligent risk analysis, early warning and optimization suggestions for command and control personnel, and reducing a fault occurrence rate.

The present invention relates to the field of industrial intelligent predictive maintenance, and in particular to an interpretable deep feature fusion network-based industrial intelligent predictive maintenance method, comprising: acquiring gearbox vibration data comprising noise; performing preliminary extraction and noise suppression on features of the acquired data by establishing an interpretable feature extraction module having a physical information constraint; integrating multi-scale features comprising long-distance and local dependencies by means of a dual-branch feature fusion module having global and local feature fusion capabilities; performing dimensionality reduction on a high-dimensional feature and generating an output by means of a classifier to obtain a final fault identification result; and performing interpretability analysis on a diagnosis process of a model. In the present invention, by embedding the signal processing technology having a well-defined physical theory support into a deep neural network, the interpretability and reliability of model inference results are effectively improved while the fault identification accuracy of the model is improved.

System and method for implementing advanced sleep modes in an O-RAN, the method includes collecting measurement data for training an AI / ML model; based on the collected measurement data, training an A / ML model and deploying the AI / ML model in the nRT-RIC; activating the trained AI / ML model in the nRT-RIC; monitoring energy optimization data for AI / ML model inference from an open radio unit (O-RU) via an E2 node; activating at least one advanced sleep mode (ASM) in the nRT-RIC; based on the activation of the ASM, collecting data to temporarily deactivate O-RU components; based on the activated AI / ML model and the ASM, evaluating, the collected data to temporarily deactivate O-RU components; based on the evaluating, requesting to initiate the ASM to the O-RU; based on the ASM initiation request, implementing the ASM, by the E2 node and the O-RU.

The invention discloses a welded pipe conveying abnormity prediction method and system based on large model reasoning, and aims to solve the problems that multi-source data is difficult to align, cross-station false correlation is caused, prediction lacks executable positioning and time sequence, and linkage control reliability is insufficient. Event alignment is carried out by taking a controller edge signal and an encoder zero position as time anchor points, a production line topology semantic graph containing time delay, capacity and interlocking attributes is constructed, and topology reachability and physical time delay constraints are applied in a self-attention long sequence model to carry out multi-step rolling prediction. And outputting a risk probability, refining the risk probability to spatial positioning of a roller way section or a shaft and the minimum executable intervention time, and generating a risk interval in combination with uncertainty estimation and calibration so as to drive an upstream beat self-adaptive speed reduction, shunting or stopping strategy. The technical effects of improving accuracy and interpretability, reducing false alarm and missing alarm, ensuring that linkage can be executed in advance and meeting edge time delay budget are achieved.

The invention discloses a battery full life cycle intelligent management method and system based on a large model, and the method comprises the following steps: S1, collecting the operation data of a battery, and carrying out the preprocessing; s2, inputting the pre-processed sample into a pre-trained Transform encoder model, and extracting a time sequence and cross-stage characteristics; s3, executing model reasoning, outputting a state index, and generating a battery state vector; s4, identifying an abnormal category and a position in combination with the working condition information; s5, generating a dynamically optimized battery management strategy based on the battery state index and the abnormity identification result; s6, deploying a lightweight model at the edge device, executing local reasoning and uploading data; s7, the cloud updates the model through self-supervised training and issues the model; and S8, repeatedly executing the steps S1 to S7, and carrying out optimized closed-loop management. According to the invention, large model modeling and an edge cloud cooperation mechanism are fused, and intelligent sensing and dynamic management of the whole life cycle of the battery are realized.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as medical health and financial science and technology, and discloses a model quantitative reasoning acceleration method, device, equipment and medium. The method comprises the steps that an input text is divided into a plurality of processing blocks, importance scoring is conducted on the non-first processing block, and calculation precision formats are distributed according to scoring results; determining a unified quantization configuration of each processing block; dividing the network modules into configuration sharing groups, and sharing quantitative configurations of corresponding processing blocks in the groups; and executing block-level quantization inference according to the unified quantization configuration, and generating a model inference result. The quantitative configuration of each processing block is uniformly determined on the basis of the token importance score, and the configuration is multiplexed in the network module group, so that block-level precision distribution and parallel quantitative reasoning are realized, the video memory overhead and the configuration time overhead are greatly reduced while the reasoning precision is guaranteed, and the reasoning efficiency is improved. And the execution efficiency and the video memory utilization rate in the long text reasoning task are effectively improved.

The invention discloses a MoE large model reasoning optimization method and device based on expert module dynamic scheduling, and relates to the technical field of large model reasoning optimization. The method comprises the steps of performing pre-reasoning through a MoE large model according to a dialogue text data set to obtain a first evaluation score set; performing value optimization on the GPU candidate expert quantity value set through an expert cache hit rate calculation method to obtain a GPU candidate expert optimized value set; cPU expert module dynamic scheduling is carried out based on the relation curve of the expert score ascending value-the transmission expert number, and a CPU expert scheduling index list is obtained; gPU expert module dynamic supplementation is carried out according to the first evaluation score set and the CPU expert scheduling index list, a GPU expert supplementation index list is obtained, re-reasoning is carried out through a MoE large model, and a reasoning result text data set is obtained. The invention relates to a large model reasoning optimization method for balancing model reasoning speed and output result quality of a MoE large model.

The embodiment of the invention provides a model reasoning method, a computer program product and a chip. In the model reasoning process, the hidden state of each lexical element in each layer can be stored, and when the key value cache of the lexical elements needs to be used, the key value cache of each lexical element in each layer of the model can be recovered based on the hidden state and the key value projection weight matrix. According to the key value cache recovery scheme provided by the embodiment of the invention, the key value cache recovery can be realized by using the computing resource and the data transmission bandwidth resource of the chip at the same time at relatively low overhead instead of singly using one resource, so that the key value cache recovery efficiency can be greatly improved, and further, the model reasoning efficiency is improved.

The invention discloses a track surface defect detection system for steel manufacturing based on YOLOv8, which belongs to the technical field of track defect detection and comprises an image acquisition device, a server, a preprocessing module, a model reasoning module, an evaluation feedback module and an alarm linkage module. The image acquisition device, the preprocessing module, the model reasoning module, the evaluation feedback module and the alarm linkage module are respectively connected with the server. According to the method, the deformable convolution structure is integrated in the YOLOv8 detection head, and the scale attention mechanism unit and the multi-scale feature fusion unit are introduced, so that high-recall-rate and high-precision positioning can be realized for various morphological defects such as long-strip-shaped cracks and small-size pitting corrosion, and the defect classification accuracy is improved by more than 10%.

The invention discloses a multi-modal large language model training-free acceleration method based on visual token efficient processing, and the method comprises the following steps: obtaining multi-modal question and answer data, and dividing the multi-modal question and answer data into a verification set and a test set; inputting the verification set into the target multi-modal large language model, and sorting the redundancy of each layer of the model through a search method; according to the redundancy ranking, inputting the test set into the target multi-modal large language model, and obtaining the redundancy of each layer of the target multi-modal large language model; and according to the redundancy, carrying out an acceleration operation about visual token processing on a part of layers of the target multi-modal large language model. According to the method, the characteristic that the computing power required by the visual token is less than that required by a text token is utilized, the redundancy layer in the large language model is positioned, and the self-attention operation and the feedforward neural network operation about the visual token are optimized, so that the model reasoning efficiency is greatly improved.

The invention discloses a data processing method and system, electronic equipment, a storage medium and a computer program product, and relates to the technical field of large model technology and key value caching. The method comprises the following steps: acquiring a plurality of visual marks, a plurality of text marks and initial key value data corresponding to a visual language model; determining a key text mark in the plurality of text marks by utilizing the initial key value data; according to the initial key value data and the distribution positions of the key text marks in the multiple text marks, importance evaluation is conducted on the multiple visual marks, an evaluation result is obtained, and the evaluation result is used for representing cross-modal attention weight distribution between the multiple visual marks and the key text marks; and according to an evaluation result, performing cache compression processing on the initial key value data to obtain target key value data. According to the method and the device, the technical problem that the model reasoning efficiency is influenced due to high key value data caching overhead of a visual language model in related technologies is solved.

The invention relates to the technical field of behavior recognition, and discloses a lightweight abnormal behavior recognition system and method based on edge computing, and the method comprises the steps: obtaining multi-dimensional heterogeneous behavior observation data covering a target region through an edge side behavior collection node system, and constructing a behavior dynamic feature vector set which can be iteratively updated; performing structure self-adaptive decoupling processing on the behavior dynamic feature vector set, and recording the fluctuation convergence rate of an abnormal category in real time in a model iteration process; judging the behavior recognition stability in the model reasoning stage, and constructing a behavior transfer trajectory map in combination with the environmental transaction interference factors; extracting density disturbance parameters of the abnormal behaviors, and generating a behavior intervention evaluation result set; and performing hierarchical risk judgment on the current identification behavior result, and automatically generating an edge execution regulation and control instruction set. The method has the advantage of improving the efficiency.

The invention discloses a welding defect classification method and system based on deep learning, and the method comprises the steps: collecting a welding image, taking the welding image as a training sample in a training set, and carrying out the preprocessing of the welding image in the training set; constructing a feature fusion CNN image recognition and classification model; training a CNN image recognition and classification model by using the training sample to obtain a trained CNN image recognition and classification model; and inputting a welding image to be classified and recognized into the trained CNN image recognition and classification model, and obtaining a defect category to which the welding image belongs through model reasoning. According to the method, the defect identification precision is effectively improved, the feature extraction process is optimized, and the real-time detection capability is ensured.

The invention discloses a water quality prediction system and method based on machine learning, and the system comprises a data collection and preprocessing module which is used for collecting and preprocessing multi-source monitoring data; the teacher model module is used for constructing a Shenchang differential equation model as a teacher model and outputting a prediction result of the target water quality index; the student model module is used for constructing a lightweight neural network model as a student model to perform structure optimization training; the trajectory evaluation module is used for calculating predicted trajectory similarity of the teacher model and the student model and optimizing structural parameters of the student model; the model reasoning module is used for calling the optimized student model to generate a prediction result of the target water quality index; and the result output module is used for outputting a prediction result and providing a display and storage interface. According to the method, high-precision, light-weight and sustainable self-adaptive prediction of water quality time sequence data is realized by fusing Shenchang differential modeling and a trajectory similar distillation optimization mechanism.

The invention provides a load identification method and system for a cloud edge collaborative architecture, and the method comprises the steps: dividing a calculation task into a lightweight task and a complex calculation task through introducing a distributed calculation model; the edge device is responsible for executing lightweight tasks such as time sequence waveform data preprocessing and feature extraction, effectively filtering noise data and reducing transmission of redundant information; the cloud server is responsible for complex model reasoning, global optimization and deep analysis of historical data, so that cooperative processing of edge computing and cloud computing is achieved, a task allocation strategy is flexibly adjusted through a dynamic task scheduling mechanism according to the real-time resource state, the task priority and the computing complexity, and the task allocation efficiency is improved. And the network bandwidth pressure and the cloud computing power load are further reduced. The method has the advantages that the real-time performance of task processing in the Internet of Things system, the stability of the system and the accuracy of an identification result are improved.

The load balancer of the multi-model reasoning service comprises a scheduler and a detector, and the detector detects the working load pressure of each queue system in a cloud service cluster. When the working load pressure of the queue system with the maximum working load pressure and the working load pressure of the queue system with the minimum working load pressure in the cloud service cluster meet scheduling conditions, the scheduler schedules one reasoning service instance from the queue system with the minimum working load pressure to the queue system with the maximum working load pressure; the scheduling condition comprises that the maximum working pressure in the cloud service cluster is greater than the product of the minimum working pressure and the threshold value. According to the load balancer and method for the multi-model reasoning service, the load balance of each queue system in a cloud service cluster can be effectively realized, so that the processing efficiency of the reasoning service of the cloud service cluster is improved; compared with a traditional greedy enumeration strategy, the load balancer and method for the multi-model reasoning service have more excellent performance in the aspects of working load, response time and response time distribution accuracy.

The invention discloses a model reasoning performance optimization method and device, equipment and a storage medium, and the method comprises the steps: responding to a received reasoning request, recognizing the structural features of a target reasoning model, and determining the type of the target reasoning model according to the structural features, the reasoning request comprises request parameters, the target reasoning model is used for executing the reasoning request, and the target reasoning model is used for executing the reasoning request; determining a first resource allocation according to the type of the target inference model and the request parameter, obtaining system load data, determining a system load state level according to the system load data, determining a second resource allocation according to the first resource allocation and the system load state level, and calculating the inference request according to the second resource allocation to obtain an inference result, through the method, the resource utilization rate can be optimized, and the system throughput can be improved.

The invention discloses a power equipment fault diagnosis system and method based on edge cloud cooperation. The system comprises an edge end module and a cloud end module. The edge end module is deployed in a power equipment site, is embedded with a lightweight diagnosis model, collects power equipment operation state parameters in real time, executes localized preliminary fault identification and alarm judgment, extracts key characteristic quantities, and uploads a processing result to the cloud end module through a network communication protocol; the cloud module is deployed in a data center or a control platform, and performs complex model reasoning, cross-device historical data comparison, fault depth research and judgment and model updating and distribution according to the characteristic quantity data uploaded by the edge module; the edge end module and the cloud end module perform data interaction through an FTP, MQTT or 5G protocol, a model trained by the cloud end can be automatically distributed to an edge end to realize rapid deployment and switching, and equipment fault diagnosis is realized. According to the invention, through a task division cooperation and data interaction mechanism, an efficient and low-delay fault diagnosis process is realized.

The invention provides an end side model reasoning method and device based on an RWKV architecture, electronic equipment and a storage medium, and the method comprises the steps: obtaining a target input request of a target object, and converting the target input request into target model input data; loading a historical reasoning state corresponding to the target input request in a preset state storage space; determining a corresponding RWKV core operator according to the hardware platform type of the terminal equipment; based on the RWKV core operator, performing reasoning calculation on the target model input data and the historical reasoning state to obtain an output token sequence; wherein in the reasoning calculation process, the real-time reasoning state of the large language model is stored in a preset state accelerator memory for multiplexing; converting the output token sequence into a text format and outputting the output token sequence; and updating the historical reasoning state according to the real-time reasoning state after reasoning calculation. According to the method, calculation optimization and hardware acceleration can be carried out on the large language model of the RWKV architecture, so that the reasoning performance of the RWKV architecture model is improved on the end side.

The invention provides a lightweight multi-model collaborative edge intelligent target detection system and a lightweight multi-model collaborative edge intelligent target detection method, belongs to the technical field of edge target detection, and aims to solve the problem that a traditional target monitoring scheme depends on a cloud server to carry out deep learning model reasoning; in order to solve the problem that high-precision and low-delay real-time target monitoring cannot be realized on a resource-limited edge device, the detection system comprises an edge calculation module, an image acquisition module and a storage module. The detection method comprises the following steps: acquiring a to-be-detected image, and calling an IPS module through a performance core and an energy efficiency core to pre-process the acquired image; optimizing the YOLO model, and inputting the preprocessed image into a deep learning model; performing target detection on the preprocessed image data through a deep learning model; and a detection result is input into the storage module for storage and is uploaded to equipment connected with the peripheral interface for visual display and a remote monitoring center.

The invention discloses a lightweight real-time radio frequency fingerprint identification method based on streaming jump connection, and belongs to the field of communication signal processing. The implementation method comprises the following steps: adopting a WiSig data set as a training set and a test set of a neural network; and replacing a two-dimensional convolutional layer in the ResNet network with a one-dimensional convolutional layer. The ADC information sampling throughput in the edge device is greater than the reasoning throughput of the radio frequency fingerprint model, a plurality of input branches are added at different depths of the radio frequency fingerprint model, and the multi-input branch structure enables the generation time of the feature patterns needing to be fused to be consistent, thereby avoiding the distribution of the storage space. And receiver distortion features and channel noise features are removed from the same kind of radio frequency fingerprint information in different time periods within the preset time. Fusion feature fingerprint identification information is used as input of a classifier to obtain a more accurate prediction vector, a vector output by a full connection layer is mapped into a probability value through a Softmax function, a neural network is trained through a cross entropy loss function and an SGD optimizer, and radio frequency fingerprints are identified through the trained neural network.

The invention discloses an inference service deployment method, electronic equipment and a storage medium, and the method comprises the steps: responding to the creation of an inference service, reading a model information configuration table and an engine information configuration table, and carrying out the matching processing of the model information configuration table and the engine information table according to a pre-configured model name during the creation of the inference service, processing resources, inference engine mirror image identifiers and inference engine starting parameters which can be used for loading inference services on the container scheduling platform are obtained, and workload metadata used for bearing the inference services are created based on the processing resources, the inference engine mirror image identifiers and the inference engine starting parameters; the deployment of the inference service on the container scheduling platform is realized by distributing the workload metadata to the target cluster node. Through the method, the technical problem of relatively low deployment efficiency caused by manually configuring the parameters in the workload metadata depending on manpower in related technologies is solved, and the technical effects of simplifying the deployment process of the model reasoning service and improving the deployment efficiency are achieved.

The invention relates to a multi-model time division multiplexing and parallel loading reasoning service method and system, and the method comprises the steps: receiving a user model reasoning request, and searching a corresponding model according to the user model reasoning request; deploying part of parameter layers of the model required by reasoning into a GPU (Graphics Processing Unit); inputting the user model reasoning request text into a parameter layer deployed by the GPU for calculation; when the partial parameter layers are calculated, loading the residual parameter layers of the model to the corresponding specified GPU; after reasoning calculation is completed, the parameter layer is unloaded and returned to the CPU, and a reasoning result is returned. A GPU device cluster is used for carrying out reasoning service on the models, cooperation among device clusters of multiple models is achieved, and the reasoning time delay of each model request is reduced. And under the condition of reserving and occupying fewer system video memories, the same and even better reasoning speed can be achieved. The model deployment and scheduling process is automated, and the deployment cost of the model is reduced as much as possible under the condition that the SLO requirement of each model request is met.

The invention discloses an image denoising and fringe removing method based on blind spot regularization, which comprises the following steps of: constructing a double-output blind spot network, respectively taking image reconstruction branch output and fringe estimation branch output of the double-output blind spot network as regularization constraint terms, and carrying out joint modeling on a clear image and fringe components through implicit network prior, random noise is removed by using blind spot regularization; a direction representation shuffling technology meeting J-invariance is introduced, and image and stripe separation is realized through multi-direction feature decomposition and vertical direction feature enhancement; in the model reasoning stage, scale-adjustable feature resampling operation is carried out on the input features, the blind spot receptive field is expanded, and the image reconstruction quality is optimized; and outputting the denoised clear image and the estimated stripe component by alternately optimizing the joint loss function of the dual-output blind spot network. According to the method, the advantages of a traditional denoising method based on a model and a method based on self-supervised learning are combined, and a new thought is provided for denoising and stripe removing tasks.

According to the lightweight helicopter fault diagnosis method and device based on cloud edge cooperation and the medium, a dynamic cooperative distributed intelligent diagnosis system is constructed between the cloud end and the edge end, so that efficient lightweight reasoning of the edge end and centralized optimization training of the cloud end are realized; therefore, an aviation health management platform with self-learning, self-adaption and online updating capabilities is constructed. The whole system adopts a cloud-edge-end three-level architecture, wherein the end side is responsible for data acquisition and preprocessing; the edge side undertakes real-time diagnosis and lightweight model reasoning; and the cloud is responsible for global training, model scheduling and strategy optimization. Cyclic interaction of model parameters, task instructions and diagnosis results is achieved between the cloud and the edge through a secure communication link, and a closed-loop intelligent updating mechanism is formed. According to the method, the real-time performance, the computing power efficiency, the model generalization ability and the system adaptability of a fault diagnosis system are remarkably improved.

The technical scheme can be applied to the field of financial science and technology / medical health. The invention discloses a mercuric chloride chip-based large model reasoning operator optimization method, device and equipment, and the method comprises the steps: carrying out the blocking processing of original input data according to the parallel calculation capability of a mercuric chloride chip, and generating the blocking data of an adaptive chip calculation unit; optimizing a memory access path of a matrix multiplication operator by combining a memory hierarchical structure and a calculation core type of a mercuric chloride chip based on the block data, and adjusting a sliding step length and a filling mode of convolution operation; a plurality of operators continuously executed in the large model are fused into a composite operator, the data storage process of the composite operator is optimized, and collaborative execution is achieved by dynamically allocating computing resources; and integrating and decoding block calculation results after collaborative optimization, and adjusting an input data block strategy and operator execution parameters through a verification feedback mechanism to form closed-loop optimization. According to the technical scheme, the reasoning efficiency of a large model can be improved.

The invention discloses a coal seam frequency resonance seismic exploration system and method based on deep learning. The method comprises the following steps: S1, arranging passive source seismic equipment to collect background waveform data; s2, performing spatial autocorrelation spectrum analysis, and extracting a frequency dispersion curve; s3, speed inversion is carried out, and a speed profile map is output; s4, constructing a DeepLabV < 3 + > model to identify geological anomalies; s5, performing image preprocessing to generate standardized input; s6, performing model reasoning to obtain a segmentation result graph; s7, generating a structure map and a risk map in combination with the coordinates; and S8, exporting an interpretation result in a structured format. According to the method, a seismic data processing flow combining a spatial autocorrelation method and a DeepLabV3 + model is adopted, and automatic extraction of coal seam frequency resonance information and intelligent recognition and visual interpretation of a geological structure are achieved.

The invention belongs to the field of photovoltaic technology, and discloses a knowledge graph and vector retrieval enhancement-based photovoltaic field large model efficiency improvement method. Comprising a knowledge graph construction process and a retrieval reasoning process, the knowledge graph construction process is to construct a photovoltaic field proper noun library and a photovoltaic field vector expert knowledge base, and fuse generated knowledge graphs to generate a photovoltaic field comprehensive knowledge graph; the retrieval reasoning process is large model text question answering based on vector retrieval and question enhancement, large model reasoning question answering based on knowledge graph enhancement and large model role question answering based on historical question answering recall. According to the method, spatial and temporal distribution characteristics and data timeliness requirements in the photovoltaic field are considered, and knowledge graph fusion of the time dimension and the space dimension is realized.

The present application specifically relates to the technical fields of computer vision and pattern recognition. Disclosed is a continual learning method based on hierarchical adaptive optimization for a large model. In the method, a current task representation is obtained on the basis of an average representation of each portion of samples in all training data involved in a task, and a similarity score between the current task representation and each of all stored known task representations is calculated. If the similarity score is greater than a preset threshold, model structure expansion is performed, and the current task representation in a task selector is randomly initialized; otherwise, the model structure and task representation of a known task with the highest similarity are reused. During training, current task data is used to train a current task-specific structure and the current task representation. Finally, by means of hierarchical training of each task, a hierarchical model consisting of a backbone network, task-specific structures and the task selector is obtained. The model can adaptively query a task-specific structure on the basis of an input to complete model inference.

The invention discloses an artificial intelligence large model reasoning acceleration method and system based on a GPU and an NPU, and relates to the technical field of large models. The invention discloses an artificial intelligence large model reasoning acceleration system based on a GPU (Graphics Processing Unit) and an NPU (Network Processing Unit). The system comprises a reasoning information shunting module and a reasoning data acceleration module, according to the method, by combining input data features, model structure dynamic control and heterogeneous computing resource collaborative scheduling, highly-adaptive large model reasoning optimization is realized, accurate matching of computing resources and data complexity is realized, and the overall reasoning throughput and response speed are remarkably improved; a dynamic scheduling mechanism based on a strategy output model is adopted, GPU / NPU calculation tasks are reasonably distributed, resource idling and congestion are avoided, the hardware utilization rate is improved, and the method is particularly suitable for multi-task concurrent and high-frame-rate video scenes.