771 results about "Model compression" patented technology

The invention discloses an adaptive question-answering system based on knowledge distillation and multi-modal dynamic fusion, and the system comprises a knowledge distillation module which is used for migrating knowledge of a teacher model pre-trained on corpora in the communication field to a lightweight student model, achieving model compression through optimizing a distillation loss function, and obtaining a multi-modal dynamic fusion model; the loss function comprises a soft label output by the teacher model and a KL divergence constraint output by the student model; the multi-modal knowledge fusion module comprises a feature extraction unit, a self-adaptive weighting unit and an attention fusion unit; the self-adaptive inference engine comprises a semantic analysis unit; according to the cross-modal reasoning method and system, semantic alignment of equipment parameters, protocol texts and topological graphs is achieved through the multi-modal dynamic fusion technology, and the cross-modal reasoning accuracy is improved; compared with an original model, the lightweight student model has the advantage that the reasoning speed is increased in a protocol analysis task.

A technique uses a machine-trained model to generate a response based on a prompt which expresses current input information and abstract token information. The abstract token information summarizes a full dialogue history of a dialogue, and is generated by the model itself. The technique reduces the size of the prompt by incorporating the abstract summary information in lieu of the full dialogue history. A training system trains the machine-trained model by successively improving the predictive accuracy of the machine-trained model, while rewarding the machine-trained model based on an extent to which the machine-trained model compresses instances of abstract token information.

The invention discloses a field specialized large model fine tuning and deployment method and system based on adaptive optimization, belongs to the technical field of artificial intelligence and machine learning, and aims to solve the technical problem of how to improve the rapid adaptation capability of a large model on small-scale field data. In order to meet the requirements of special fields of law, medical treatment, finance and the like on professional terms and complex contexts, the technical scheme adopted by the invention comprises the following steps of: data processing and sample generation: performing cleaning, feature extraction and small sample expansion on field data, and generating a high-quality training sample through a field feature guide mechanism; small-sample fine tuning and migration: realizing rapid field adaptation of a large model through a small-sample learning technology and dynamic Prompt optimization, and reducing dependence on large-scale annotation data in combination with cross-field migration learning; compressing and optimizing the model; performing automatic deployment and collaborative reasoning; and monitoring and adaptive optimization are carried out.

According to the weld joint positioning and defect detection system and method based on deep learning, the target detection pyramid network structure suitable for different image sizes is applied to weld joint detection, and the adaptability of intelligent weld joint detection to the image sizes is improved; meanwhile, a defect labeling mode of a free rectangular frame is selected, so that the identification accuracy of positioning is improved; welding seam positioning and defect identification are carried out by adopting a deep learning method based on an FPN network structure through marking defects of welding seams, air holes, welding beadings and pits in an image data set, and training of target detection and semantic segmentation functions is completed; according to the method, model compression is carried out by adopting double-correlation knowledge distillation, correlation between spatial positions and correlation between channels in a feature map are considered at the same time, and two types of correlation information are migrated from a complex model (teacher model) to a compact model (student model), so that compression of the model is realized, and balance between segmentation precision and reasoning speed is achieved.

The invention relates to the technical field of corn kernel quality detection, in particular to a corn kernel quality detection model construction method and system based on multi-source data fusion, and the method comprises the following steps: S1, multi-source data collection: collecting apparent morphology data of corn kernels through a multi-spectral imaging device, synchronously utilizing a near-infrared spectrometer to obtain spectral data of internal components of the corn kernels, and measuring structural density characteristic data of the corn kernels in combination with a sonic sensor; s2, multi-modal feature construction: forming a multi-modal feature matrix; s3, dynamic weighted fusion: generating a mixed feature vector; s4, constructing a dual-channel neural network: constructing a dual-channel deep neural network based on the generated mixed feature vector; and S5, model compression and deployment optimization: generating a lightweight detection model suitable for the embedded device. According to the invention, multiple requirements of an agricultural field on real-time performance, precision and deployment flexibility are met.

The invention belongs to the technical field of model training, and particularly relates to a large model increment training method and system based on dynamic sparsification. The method comprises the following steps: S1, evaluating the parameter importance of a large model by adopting a multi-dimensional evaluation method, and reflecting the contribution of parameters to the performance of the large model; s2, performing dynamic sparsification control on the large model structure by adopting a self-adaptive structure adjustment method; s3, performing incremental training management on the large model by constructing a capacity-adjustable empirical playback buffer pool and proposing a multi-objective loss function; and S4, carrying out model compression optimization on the large model by adopting a mixed precision quantification strategy. The method has the characteristics that the network structure can be dynamically adjusted by evaluating the importance of model parameters in real time, so that the efficient training is realized while the model performance is ensured.

The invention discloses a road safety early warning method and system based on a mixed precision quantification visual large model, and the method comprises the steps: collecting road traffic safety videos and pictures, and carrying out the preprocessing, data enhancement and marking, thereby forming a diversified data set; a pre-trained visual large model is selected as a teacher model, after fine tuning, output layer and middle layer knowledge is extracted, key features are weighted, and meanwhile, a lightweight neural network is taken as a student model, same input is received, and prediction and middle feature maps are output. And inputting data into the two models and the student model to carry out mixing precision quantification forward propagation, constructing a total loss function containing tasks, knowledge distillation and quantification learning loss, and updating parameters through back propagation. And after training is completed, exporting a quantitative model, and deploying the quantitative model to an edge computing platform to realize safety early warning. The lightweight model can realize rapid reasoning on edge equipment such as a vehicle-mounted road side, and the problem that performance and efficiency are difficult to consider in a traditional model compression method is solved.

The invention relates to the technical field of security management, in particular to an AI-based intelligent security remote inspection and control method, which comprises the steps of front-end intelligent equipment deployment, intelligent inspection execution, data processing and intelligent analysis and remote control and linkage response. Compared with the defects of incomplete information and high false alarm rate due to the fact that equipment appearance anomaly detection mainly depends on single-modal data in the prior art, the scheme adopts multi-modal data preprocessing and feature extraction, constructs a cross-modal alignment network architecture, dynamically fuses laser radar, RGB-D images and IMU data by using a self-attention mechanism, and improves the detection accuracy of the equipment appearance anomaly. According to the method, more accurate equipment appearance abnormity identification is realized by combining environment self-adaptive adjustment, and the model is compressed and deployed to an edge end through a knowledge distillation technology, so that real-time reasoning and analysis are realized, the intelligent level of security inspection and the accuracy of abnormity detection are remarkably improved, the false alarm rate is reduced, and the practicability and reliability of the system are enhanced.

The invention provides a personalized fitness system and method based on multi-modal data and an adaptive large model. According to the method, multi-modal data are integrated, and heterogeneous data collaborative analysis is realized by using a space-time alignment algorithm and a confidence coefficient weighting mechanism. A multi-task learning framework is adopted, physiological prediction, exercise risk early warning and psychological incentive strategy generation tasks are synchronously processed, a user stage target is adapted through a dynamic attention mechanism, and federal learning and transfer learning technologies are combined. A nonlinear periodic planning engine based on reinforcement learning dynamically adjusts training load and action difficulty according to real-time biomechanical simulation results and recovery state evaluation, and meanwhile, a lightweight model compression technology and end-side reverse dynamics calculation are adopted. Based on the scheme, the exercise performance prediction precision and the early warning timeliness are improved, and the exercise loss risk caused by overtraining is reduced; the cold start data bottleneck is broken through; low-delay virtual coach interaction and privacy protection are realized; and dynamically adjusting the training intensity and the incentive strategy.

The invention provides a big language model pruning method and device, a storage medium and a program product. The method comprises the steps of obtaining a pre-trained big language model and a corresponding text data set; dependent neurons are activated through iteration, interdependent coupling groups in the large language model are recognized, and the coupling groups serve as basic units of pruning; based on the coupling group, performing coarse-grained evaluation and fine-grained evaluation on the parameters in the group, and fusing and calculating the importance of the parameters to generate a pruning mask; redundant parameters in the model are removed through pruning operation according to the pruning mask; performing parameter optimization on the pruned model, and performing fine tuning through a text data set to generate a target large language model; and deploying the target large language model to a computing device, executing a text generation or semantic analysis task, and counting the task accuracy rate and the model compression rate. According to the method, the parameter quantity of the model is effectively reduced, so that deployment is simple, and the downstream task processing accuracy of the pruned model is improved.

Systems and methods for optimizing large language models (LLM) with domain-oriented model compression. Importance weights for general knowledge in a trained LLM, pretrained with deep learning, can be determined by computing the error when removing a weight from the trained LLM. The trained LLM can be iteratively optimized to obtain a domain-compressed LLM with domain knowledge while maintaining general knowledge by: fine-tuning the trained LLM iteratively with domain knowledge using the importance weights for general knowledge to obtain a fine-tuned LLM; determining importance weights for domain knowledge in the LLM with a regularization term by using gradient descent to optimize parameters when the fine-tuned LLM is trained with domain knowledge; and pruning learned knowledge based on importance weights for domain knowledge. A corrective action can be performed on a monitored entity using the domain-compressed LLM.

The invention relates to the technical field of artificial intelligence and edge computing, in particular to an end-side cloud collaboration system based on a hybrid scheduling strategy. The end-side cloud cooperation system based on the hybrid scheduling strategy comprises a model segmentation module, a state sensing module, a reasoning scheduling module, a model compression and deployment module, an edge optimization engine and a communication synchronization module. According to the end-side cloud cooperation system based on the hybrid scheduling strategy, elastic deployment and dynamic reasoning of a complex model in a multilayer heterogeneous environment are supported, the system state can be sensed in real time, a scheduling path can be optimized, and the robustness of the system is improved; and in combination with model compression and edge operator optimization, the reasoning efficiency is remarkably improved, the communication load is reduced, and then low-delay cooperation between the terminal and the cloud is ensured.