55 results about "Process training" patented technology

The invention discloses a multi-modal content auditing method and system and a computer storage medium, and relates to the technical field of content auditing, and the method comprises the steps: collecting texts, pictures, audio and video resources on the Internet in real time; pre-training texts, pictures, audio and video resources through self-supervised learning to generate a multi-modal large model base; the multi-modal large model base adapts to the auditing task through fine tuning training, and a multi-modal model is obtained; utilizing a prompt project to guide the multi-modal model to generate an understanding question and answer data set as a fine tuning data set; based on the fine tuning data set, constructing a multi-modal auditing model through iterative fine tuning process training; according to the method, the auditing rule and the situation adaptability scoring function are dynamically generated, context perception analysis is carried out on the real-time auditing request, a more accurate auditing strategy is generated, the method has remarkable technical advantages in the field of multi-modal content auditing, and powerful support is provided for achieving an efficient and safe network environment.

The invention discloses an SDH communication equipment fault maintenance simulation teaching method based on digital twinning. The method comprises the following steps of S1, equipment simulation, S2, fault scene definition, S3, fault injection, S4, fault simulation, S5, fault diagnosis, S6, fault repair and S7, evaluation and feedback. The system has the advantages that a real SDH equipment fault scene can be simulated, fault checking and repairing training close to actual combat can be provided for students, excessive consumption and high purchase cost of entity equipment are avoided, virtual simulation of an SDH communication equipment fault mode is realized by constructing a high-precision SDH communication equipment digital twinborn body, and the simulation efficiency of the SDH communication equipment fault mode is improved. And fault processing training close to a real environment is provided for students. The invention provides an efficient, economic and safe SDH communication equipment fault maintenance skill training method so as to improve the practical ability and the troubleshooting efficiency of trainees.

The invention discloses a polyester knitted fabric surface antistatic treatment method and system, and relates to the technical field of polyester knitted fabrics, the method comprises the following steps: determining a treatment process scheme according to a target application scene, calling a sample process record, and constructing a standard process training set; constructing and training an antistatic performance prediction model based on the standard process training set in combination with a knowledge distillation mechanism; a cost evaluation factor is constructed, a process evaluation function is defined in combination with the antistatic performance prediction model and the cost evaluation factor, and the process evaluation function is associated with a penalty space; and by taking the process evaluation function as an optimization target, carrying out adaptive capacity expansion and shrinkage iterative optimization on the treatment process parameters, determining a target process parameter combination for the polyester knitted fabric according to an iterative optimization result, and carrying out surface antistatic treatment. Therefore, the technical effects of reducing the parameter adjustment cost, improving the adjustment efficiency and enhancing the anti-static treatment flexibility are achieved.

A system for generating instructions based on part from human training materials, wherein the generated instructions are used to train automated agents. The training materials may include training manuals, knowledge-base documents, articles, and other content. The training materials are processed and converted to a format that is digestible by a machine learning model. The processed training materials can be submitted as a prompt, along with role information and prompt instruction information. The prompt instructions provided with the role and training materials may direct the machine learning model to find relevant generated instructions from the provided training materials. The machine learning model processes the prompt and outputs extracted instructions from the content. The instruction document may be stored in a vector database for later use.

The invention discloses a transformer substation building air conditioner control model training method and system, and the method comprises the steps: carrying out the verification and cleaning of each piece of obtained training data and target data, obtaining a plurality of pieces of processed training data and processed target data, inputting each piece of processed training data into a constructed initial control model, and carrying out the verification and cleaning of the obtained training data and target data, the initial control model is used for processing the training data, so that a fuzzification layer of the initial control model carries out fuzzification processing on the processed training data to obtain corresponding membership parameters, according to the membership parameters, a recursion layer is used for processing the time sequence of the processed training data to obtain corresponding feature data, and a decision layer is used for analyzing the feature data to obtain the feature data; and obtaining model temperature data, then obtaining a matching degree according to the model temperature data, and updating parameters in the initial control model according to the matching degree. According to the air conditioner control model obtained through the method, the temperature of each room in the transformer substation can be accurately predicted, and energy wasted by each air conditioner is reduced.

A computer implemented method of managing a first model that was trained using a first machine learning process and is deployed and used to label medical data. The method comprises determining (202) a performance measure for the first model, and if the performance measure is below a threshold performance level, triggering (204) an upgrade process wherein the upgrade process comprises performing further training on the first model to produce an updated first model, wherein the further training is performed using an active learning process wherein training data for the further training is selected from a pool of unlabeled data samples, according to the active learning process, and sent to a labeler to obtain ground truth labels for use in the further training.

The invention discloses a bearing fault detection method based on knowledge distillation. The method comprises the steps of obtaining a bearing operation process training data set; preprocessing the acquired data to obtain a target data set; pre-training the offline CNN model by using the target data set to obtain a teacher model, extracting a soft label of the teacher model and constructing a student model; training a teacher model and a student model by using the target data set, and extracting a soft label corresponding to the teacher model and a soft output probability corresponding to the student model; knowledge of the teacher model is distilled to guide student model training. According to the method, continuous wavelet transform is adopted to convert an image from a one-dimensional vibration signal to a two-dimensional time-frequency signal, data information contained in an original signal is better represented, a knowledge distillation method is utilized to process a teacher model, knowledge of the teacher model is transferred to a small-scale student model, the scale of the model is well reduced, and the teaching efficiency is improved. And the model complexity is reduced. And meanwhile, the student model obtains knowledge from the soft labels of different teachers, so that overfitting can be effectively reduced.

The invention discloses an intelligent physical training planning system based on big data, which relates to the technical field of intelligent physical training and comprises a personal information management module based on system architecture, a training data analysis module and a training planning optimization module. The system is characterized in that the personal information management module adopts a layered architecture design of a data input layer, a data storage layer, a data processing layer, a data access layer and a user interaction layer to ensure safe and efficient processing of data; the training data analysis module adopts an efficient data processing algorithm and an engine to quickly analyze and process training data; the training planning optimization module generates a personalized training plan by adopting a machine learning algorithm, and divides a training planning function into a personalized training planning module and a training effect evaluation and feedback module. Compared with the prior art, the method has the advantages that the data processing capability is efficient; personalized training planning is carried out; the system integration degree is high; and carrying out data visualization.

Certain aspects of the present disclosure provide techniques and apparatus for improved machine learning. In an example method, a first plurality of weights for a base model and a second plurality of weights for an adapter model associated with the base model are accessed. A quantized plurality of weights is generated based on the first plurality of weights, a first quantization scale for the first plurality of weights, and the second plurality of weights. A loss is generated based on processing training data using the quantized plurality of weights. An updated second plurality of weights is generated based on updating the second plurality of weights based on the loss. A machine learning model comprising quantized versions of the first plurality of weights and the updated second plurality of weights is deployed.

The embodiment of the invention discloses a training data processing method for a large model, which comprises the following steps of: obtaining an initial data set containing a reasoning process of the large model, determining a condition required by the large model to deduce an output result in model input of the initial data set in the reasoning process, and outputting the output result according to the condition. And updating conditions determined in the model input, so that the model input does not have conditions required by the output result of the large model any more, obtaining a training data set which is marked as incapable of outputting the result, and performing fine adjustment on the large model to be adjusted based on the training data set. According to the method, conditions necessary for outputting results are determined through the reasoning process of a large model, and then corresponding conditions in model input are updated based on the conditions, so that a training sample set does not have the conditions for reasoning a real output result any more, and the ability of training the large model to recognize the model input without the output result is achieved; and the illusion condition of a large model output result is avoided.

1. Name of the Design Product: Sulfonation Process Training and Examination Device. 2. Use of the Design Product: For sulfonation process training operations. 3. Design Key Points of the Design Product: Lies in the shape. 4. Picture or Photograph Most Indicating the Design Key Points: Stereogram.

The method performed by an electronic device may include: outputting monitoring data of a target scenario among one or more predetermined scenarios related to simulation errors, in a production mode of a semiconductor process simulation based on test data input by a user; switching from the production mode of the semiconductor process simulation to a maintenance mode; and terminating the target scenario when a user input related to simulation maintenance satisfies a maintenance condition of the target scenario while in the maintenance mode.

The present invention discloses a method for improving the performance of a neural machine translation system, and the steps are as follows: processing training data and initializing the parameters of the neural machine translation system; adjusting the generation rule of the absolute position encoding in the neural machine translation system to a multiplicative sine-cosine encoding generation rule; inputting the training data, reading the absolute position encoding into the neural machine translation system, adding it to the word vector of the input source sentence to obtain a word vector fused with position information, and feeding it into the neural machine translation model; training the neural machine translation system using the gradient descent method until convergence, and the training process is the same as that of the existing neural machine translation system; during the decoding process, for the absolute position encoding generation rule, it is kept consistent with the multiplicative sine-cosine encoding generation rule. Without changing the number of parameters and the amount of computation of the neural machine translation system, the present invention improves the recognition ability of the translation system for the word order of the input language and effectively improves the translation performance of the neural machine translation system.

The invention relates to the technical field of network security, and discloses a rebound shell detection response system and method, a medium and a product, and the method obtains tetrad information, a process parameter set and a process behavior chain in real time through Netlink, avoids missing detection caused by short process injection time, and reduces system resource occupation; a probability distribution table is constructed in the process training module to serve as a dynamic baseline, so that false alarms caused by baseline stiffness are reduced; in the engine analysis module, the characteristics and behaviors of the host layer process are analyzed in combination with a probability distribution table, and whether the host layer process is a rebound shell process or not is judged, so that the problems that traditional rule detection is easy to bypass and encrypted traffic cannot be identified are solved, and false alarms and missing alarms are reduced; the multi-dimensional depth defense principle is combined in the dynamic response module, the rebound shell process can be thoroughly eradicated, the problems that traditional detection response is delayed and blocking is not thorough are solved, and the real-time performance, the accuracy and the rapid blocking performance of rebound shell detection are improved.

The embodiment of the invention provides a model training method and device, equipment and a storage medium. The method comprises the following steps: acquiring a group of parallel configuration parameters by utilizing a state component of a model training framework to determine distributed information; using a parallelization component of the model training framework to construct a parallel plan corresponding to the to-be-trained model based on the distributed information, and generating a parallelization version of the model based on the parallel plan; and utilizing a training component of the model training framework to process the training data based on the parallelized version so as to adjust different parameters of the model in parallel. On the basis of the mode, distributed training can be carried out on the basis of the parallelized version of the model, decoupling can be achieved through all the components in the model training framework, model training is carried out on the basis of the components, developers do not need to deeply understand underlying parallel computing details, and the development efficiency is improved. The training setting and management process is simplified, and the training efficiency is improved.

1. The name of this design product: Phosgene and phosgenation process training and operation examination device. 2. Purpose of this design product: Used as a training device for chemical industry practitioners on phosgene and phosgenation process operation. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

1. Name of the design product: Chlorination process training and examination device. 2. Use of the design product: For the training and assessment combining simulation and practical operation of chlorination process. 3. Design key points of the design product: Lies in the shape. 4. Picture or photograph that best shows the design key points: Perspective view.

This invention discloses a development and training method and system based on artificial intelligence in the logistics field, including the following steps: receiving input of logistics professional training requirements, preprocessing and standardizing the input content, completing the training environment configuration and resource initialization, and obtaining clear training objectives and resource configuration parameters; based on the determined training objectives, collecting relevant data of logistics scenarios. This invention deploys full-process logistics professional training by constructing an edge-cloud collaborative training architecture, breaking the limitations of traditional training equipment and scenarios, improving the flexibility and practicality of training, processing training data through a combination of automated annotation and manual verification to improve data annotation efficiency and accuracy, quickly constructing high-quality standardized logistics training datasets, and building AI models for logistics scenarios through hyperparameter optimization and incremental training mechanisms to improve model adaptability and recognition capabilities, and lower the model development threshold.

The invention relates to artificial intelligence, and provides a model training method, a text processing method and related equipment. The model training method comprises the following steps: calling a large language model to process a training sample, and determining the probability that lexical elements in the training sample are pre-allocated to a plurality of expert networks of the large language model for processing; determining loads of a plurality of expert networks based on a plurality of probabilities corresponding to the lexical elements; determining a first expert network and a second expert network from the plurality of expert networks according to the loads and the load threshold values of the plurality of expert networks; determining a third expert network for processing the lexical elements according to the probability that the lexical elements are allocated to the second expert network; and training a large language model based on an output result of the lexical elements by the first expert network and an output result of the lexical elements by the third expert network. According to the method, the problem of overload of each expert network in the training process of the large language model can be solved while the training effect of the large language model is ensured.

The present disclosure provides a method for training a machine learning process, the method comprising: (a) obtaining identified features in a first computerized process, the identified feature is identified in a second computerization process based on an overlap between a first highest match of an unlabeled and randomly obtained feature and a second highest match of an unlabeled and correctly or wrongly indicative detected feature of the reference classification; and (b) training, by the first computerized process, a machine learning process using a training dataset of features and further based on the identified features to provide a determination of the reference classification with respect to the automatic driving application.

The invention provides a model training method and device, a task processing method and device, equipment, a medium and a product, and the model training method comprises the steps: processing training data according to a text generation model of a current training round to obtain a prediction text set and a sample label set corresponding to the training data, determining reward values corresponding to the prediction text set in a plurality of preset optimization dimensions; according to the reward value corresponding to each preset optimization dimension, determining an advantage value of each preset optimization dimension; according to the preset dimension weight of each preset optimization dimension and the advantage value of each preset optimization dimension, determining a dimension loss value of each preset optimization dimension; and training a text generation model according to the dimension loss values of the plurality of preset optimization dimensions to obtain a text generation model of the next training round. According to the embodiment of the invention, the training precision of the text generation model can be improved.

The invention discloses a self-adaptive promotion robot driving training method based on capability grading and task decomposition, and aims to overcome the defects that in the prior art, test taking is emphasized, the capability is light, feedback is extensive, and a path is rigid. According to the method, a pyramid type three-layer teaching framework is adopted, and basic vehicle control training, atomic operation fragment strengthening and comprehensive process training are sequentially carried out. The system collects operation data in real time, constructs a dynamic ability portrait based on indexes such as vehicle speed standard deviation, calculates a comprehensive score through a weighting formula, realizes self-adaptive promotion in combination with a threshold value, and supports personalized point location marking and flexible splitting training. According to the invention, transformation from test taking to ability is realized, training precision and efficiency are improved, individual demands of trainees are adapted, teaching resource configuration is optimized, and the method is suitable for intelligent driving training scenes.

The present application relates to the field of computer technology, and in particular to a method and apparatus for processing training data, which obtains an original training data set, wherein each training sample contained in the original training data set corresponds to at least two candidate labels; determines the labeling confidence of each candidate label corresponding to each training sample, and filters each candidate label corresponding to each training sample according to the labeling confidence of each candidate label; samples each training sample corresponding to each filtered candidate label so that the number of training samples corresponding to different categories of candidate labels meets a preset quantity difference condition, thereby obtaining a target training data set; and uses the target training data set to perform model training, thereby improving the reliability and balance of the training data and thereby improving the accuracy of the model training.

The utility model provides an automatic rifle live ammunition simulation process training device, and relates to the field of simulated live ammunition training, four corners inside an installation assembly are respectively provided with an installation hole, the upper side and the lower side of the installation hole are communicated in two directions, and the rear side of a guide mechanism is fixedly connected with a shooting assembly. The problems that in the prior art, although some simulation training devices exist, the simulation training devices have obvious defects in the aspects of simulation of real spot shooting feeling, operation feedback, correction guidance and the like, and the high-precision and high-efficiency spot shooting training requirements cannot be met are solved. The rack assembly is arranged at the bottom end of the servo motor A and is in meshing transmission with an out-stroke gear arranged on an output shaft at the bottom end of the servo motor A, so that when the recoil force feedback training device is used, real recoil force feedback can be simulated through meshing transmission of the driving gear and the rack assembly to be used by trainees, and then the purpose of precise training is achieved.

A method for training of machine learning processes, the method includes (a) obtaining, at a first computerized process, an identified signature, the identified signature identified at a second computerized process based on an overlap between a first top matching of signatures that are untagged and randomly obtained and a second top matching of signatures that are untagged and are correctly or erroneously indicative of a detection of a reference classification; and (b) training, by the first computerized process, a machine learning process using a training dataset of signatures and further based on the identified signature, to provide determinations for the reference classification with respect to an automated driving application.

1. The name of this design product: Amination process training and examination device. 2. Purpose of this product design: This product design is used for the training and assessment of industrial personnel on the amination process operation by combining simulation and actual operation. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

This application discloses a model training method and a cloud management platform based on a cloud management platform, which can improve model training efficiency. The method includes: a tenant sending a model training request for a specific model to the cloud management platform, whereby the tenant sets the number of queries, keys, and values ​​for the model. Based on this request, the cloud management platform determines multiple computing nodes. If the number of computing nodes exceeds the number of keys, the cloud management platform decomposes the model into multiple sub-models and deploys them on these computing nodes. These computing nodes can use these sub-models to process training data, obtaining the queries, subkeys, and subvalues. Then, these computing nodes can fuse the subkeys and subvalues ​​to obtain the keys and values. Subsequently, these computing nodes can use the queries, keys, and values ​​to complete the subsequent training of the sub-models.

The invention discloses a heterogeneous edge calculation multi-teacher federated distillation method based on course learning, and aims to reduce the influence of statistical heterogeneity on model performance on the premise of protecting the heterogeneity of an edge device model. The method specifically comprises the following steps: S1, a client performs local training by using a private data set and global knowledge, and then transmits output obtained by reasoning on a public data set to a server; s2, the server evaluates the quality of the output uploaded by each client by taking a sample as a unit, and then performs weighted aggregation to generate comprehensive knowledge; and S3, the server follows the thought of course learning, dynamically trains a global model by using comprehensive knowledge, and then sends global knowledge output by the global model to the client. And repeating the above process, and training until the global model converges. Compared with a previous federated learning method, the method has the advantages that the performance on four data sets is obviously improved, and the method is generally suitable for various training tasks.

1. The name of this design product: Fluorination process training and examination device. 2. Purpose of this product design: This product design is used for the training and assessment of industrial personnel on fluorination process operations by combining simulation and actual operation. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

This invention discloses a modular VR / AR surgical teaching system and method based on a local large-scale model. The local large-scale model training module is deployed in a local computing environment, storing structured medical knowledge and dynamically generating teaching scripts and assessment question banks. A lightweight VR / AR hardware group collects multi-dimensional user operation data and provides multi-sensory feedback. A full-process training control module, with a built-in physical simulation engine and evaluation logic, constructs a virtual surgical scene, simulates tissue mechanical changes in real time, compares user operations with standard surgical procedure models and generates error correction guidance, and generates a quantitative ability assessment report based on the entire process data. A multi-scene data mapping interface adopts a modular architecture based on a standardized intermediate communication protocol, achieving low-coupling logical isolation and dynamic integration between functional modules through a unified data exchange format and abstract interface specifications. This application adopts an edge-side deployment strategy to protect patient privacy and ensure real-time force feedback and tissue deformation rendering in the VR / AR scene.