1376 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.

In the present disclosure, a method for operating a terminal in a wireless communication may include receiving, by the terminal, a synchronization signal from a base station, transmitting a random access preamble to the base station based on the synchronization signal, receiving a random access response based on the random access preamble, performing connection with the base station after receiving the random access response, receiving at least any one of AI / ML model information and model performance feedback-related information for an AI / ML model from the base station, and performing model inference in the AI / ML model based on the AI / ML model information and determining, through model performance evaluation, whether or not to transmit MPF of the AI / ML model to the base station.

The invention discloses a power transmission line external damage prevention monitoring method based on deep learning target detection and tracking, relates to the technical field of power transmission line external damage prevention monitoring, and aims to solve the problems of poor image data acquisition quality of a scene around a power transmission line and inaccurate foreign matter recognition and tracking. According to the method, the processing speed is optimized through the YOLOv6 model, real-time monitoring of the power transmission line can be achieved, the external damage risk can be quickly responded, the YOLOv6 model can adapt to complex scenes and illumination changes, the recognition capacity in different environments is improved, the whole process automation from data preprocessing, model reasoning to result recognition is achieved, and the recognition efficiency is improved. The DeepSORT model can process complex conditions such as disappearance and re-occurrence of a target, supports real-time processing and can detect and track the target in a monitoring video stream in real time in power transmission line external damage prevention monitoring due to environmental factors and diversity of potential targets.

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 provides a reasoning service method, a processing device, equipment, a storage medium and a program product, and relates to the technical field of artificial intelligence. The large model reasoning service method comprises the following steps: monitoring first computing power resources of a plurality of decoding nodes and monitoring performance indexes of migration links between pre-filling nodes and the decoding nodes; in response to the large model reasoning task, distributing the reasoning task to a plurality of pre-filling nodes, and generating corresponding key value cache KV Cache data; performing fragmentation processing on the KV Cache data based on the first computing power resource and / or the performance index to obtain KV Cache fragments; and migrating the KV Cache fragments to the plurality of decoding nodes, so that the plurality of decoding nodes decode the KV Cache fragments based on a multi-head parallel attention balancing mechanism and / or an assembly line parallel balancing mechanism to obtain a reasoning result. According to the technical scheme, the migration efficiency and migration stability of KV Cache data can be improved, and the reasoning efficiency of a large model reasoning task can be improved in combination with a balance mechanism.

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 discloses a request management method, device and system for model reasoning. The method comprises the following steps: obtaining an observation index of a model reasoning service; index prediction is carried out according to the observation indexes, prediction indexes are obtained, and the prediction indexes comprise the target memory utilization rate of the central processing unit and the target video memory utilization rate of the graphics processing unit; determining a scheduling strategy according to the prediction index, determining a scheduling suggestion according to the scheduling strategy in combination with the request queue, and adding the scheduling suggestion into a suggestion buffer queue; when the model reasoning service executes request scheduling, the scheduling suggestion is read from the suggestion buffer queue, a target scheduling decision is determined according to the scheduling suggestion in combination with a scheduling decision of the model reasoning service, and the model reasoning service is controlled to schedule corresponding request execution model reasoning according to the target scheduling decision; the problem of unreasonable request scheduling in the model reasoning process is solved, and efficient utilization and reasonable allocation of resources are realized.

The present application discloses a method, device and related equipment for interpretability of a large model reasoning process based on Circuit and Embedding. The method of the present application first runs the large model and records the intermediate states of each hidden layer during the reasoning process. An information flow graph is constructed based on the intermediate states, in which nodes represent the Token embedding representations of each hidden layer and edges represent the computational operations between hidden layers. An attribution algorithm is used to calculate the contribution of each edge in the information flow graph to the output result, and key edges are screened according to the contribution, and the Token embedding representations of key nodes are screened in the nodes associated with the key edges. Finally, prompt instructions are used to guide the large model to interpret the Token embedding representations of key nodes to generate interpretation results. By analyzing the intermediate states, constructing the information flow graph, identifying the key paths and generating natural language explanations, the reasoning process of the large model is effectively explained, and the interpretability of the large model is enhanced.

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 ground penetrating radar image recognition method, and particularly relates to a ground penetrating radar image recognition method based on GDS-YOLOv8n, and the method comprises the specific steps: 1, constructing a ground penetrating radar image data set, and dividing the data set into a training set, a verification set and a test set; 2, a GDS-YOLOv8n model is constructed, and the GDS-YOLOv8n model is constructed by adopting a DRRB module, an SPD-Conv module, an Inner-SIOU and a detection head network; and step 3, using a GDS-YOLOv8n model to carry out identification on the constructed ground penetrating radar image data set. A DRRB module, an SPD-Conv module, an Inner-SIoU and an auxiliary training head are introduced into a YOLOv8n network model, and an identification model GDS-YOLOv8n of a GPR image is provided. And meanwhile, the GDS-YOLOv8n model subjected to TensorRT optimization is deployed on NVIDIA Jetson Orin NX edge computing equipment, so that the GPR image real-time interpretation of the mobile terminal is realized. The method is excellent in model reasoning speed and resource consumption, can accurately recognize a target in a complex environment, and meets the requirements for real-time performance and portability in practical application.

The invention discloses a method and a device for reasoning a hybrid expert model, which are used for solving the technical problem of low reasoning efficiency caused by the existing reasoning process based on the hybrid expert model. The method comprises the steps of obtaining a pre-running text data set, performing expert quantization on a preset hybrid expert model, and determining a quantized hybrid expert model; adopting a preset torch function to adjust an initial memory environment corresponding to the quantitative hybrid expert model according to the model configuration file of the quantitative hybrid expert model, and determining a target memory environment; in the target memory environment, inputting the pre-running text data set into the quantitative hybrid expert model for pre-running reasoning, and determining the average time length of model calculation; adopting a preset expert prefetching inequality to calculate the average duration according to the model, and calculating the number of prefetchable experts; and in the target memory environment, based on the number of prefetchable experts, reasoning the to-be-reasoned text data by adopting the quantitative mixed expert model, and outputting a model reasoning result.

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.