Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

43results about How to "Achieve learning" patented technology

Unstructured database federated learning collaboration method and system based on swarm intelligence

The invention provides an unstructured database federated learning collaboration method and system based on swarm intelligence, and relates to the technical field of structured data, and the method comprises the steps: training a query pattern recognition sub-model, a path planning sub-model and a resource allocation sub-model through federated learning, and constructing a swarm intelligence collaboration network. After a user query request is analyzed by the query mode recognition sub-model, candidate query paths are generated and optimized by fusing an ant colony algorithm and a particle swarm algorithm, and a query execution scheme is generated. And the resource allocation sub-model performs resource scheduling accordingly. And generating a performance optimization target for updating local model parameters of each node, and fusing the updated parameters through a security aggregation algorithm to guide the next query optimization. According to the method, the query efficiency of the unstructured database is improved, and the resource consumption is reduced.
Owner:北京科杰科技有限公司

Drug-target affinity prediction method based on multi-scale mixed attention network

The invention relates to the field of drug-target affinity prediction, in particular to a drug-target affinity prediction method based on a multi-scale mixed attention network. According to the method, global residue characteristics can be learned by protein pocket residues by utilizing a self-attention mechanism, so that the global characteristics of the protein are learned. In addition, a cross-modal feature fusion mechanism is utilized, protein and drug structural features are enhanced in sequence features, cross-modal feature fusion in entities is enhanced, meanwhile, a cross-entity interaction module is utilized to recognize key atoms of drug molecules or key residues of protein, and therefore the overall performance of the model is improved. Finally, multi-level protein feature extraction is further introduced to further extract protein features.
Owner:OCEAN UNIV OF CHINA

Multi-modal knowledge graph completion method based on neighborhood semantic enhancement

ActiveCN118966347AEnhance semantic expression abilityImprove completion resultsBiological modelsKnowledge representationKnowledge graphSemantic feature
The invention discloses a multi-modal knowledge graph completion method based on neighborhood semantic enhancement, and belongs to the field of multi-modal knowledge graphs. Specifically, firstly, a neighborhood semantic enhancement module is designed, different neighborhood information is fused into representation of a central entity, and the semantic expression ability of the model is enhanced. Then, a cross-modal attention mechanism is utilized to capture interaction and common semantic features of information among different modals, and learning of neighborhood guiding features is achieved; and comparing similarity and difference between positive and negative samples based on a comparative learning method, learning richer entity representation, and finally improving a multi-modal knowledge graph completion result.
Owner:DALIAN UNIV OF TECH +1

Binary component vulnerability identification method based on large language model

The invention belongs to the technical field of computer system security, and particularly relates to a binary component vulnerability recognition method based on a large language model. The method solves the problems of various equipment types, various instruction set architectures, different compilers, different compiling optimization levels and the like in the current Internet of Things binary component vulnerability recognition, and comprises the following steps: S100: collecting various vulnerability description information of an Internet of Things component, extracting data from the vulnerability description information, and constructing a text information data set; s200, performing text segmentation processing on a long text in the text information data set; s300, inputting the constructed text information data set into a large language model for training and optimization; and S400, detecting the binary component by using the trained vulnerability recognition large model to obtain a binary component vulnerability detection result report.
Owner:TAIYUAN UNIVERSITY OF TECHNOLOGY

Quantum strategy learning energy management method of multi-stack fuel cell hybrid power system

The invention belongs to the technical field of energy management of hybrid power systems, and discloses a quantum strategy learning energy management method and system for a multi-stack fuel cell hybrid power system, and the method comprises the steps: building a multi-stack fuel cell hybrid power system model which comprises a fuel cell power model, a lithium battery equivalent circuit model and power balance; constructing a quantum hybrid neural network, interacting with the established hybrid power system environment, distributing output power of different power sources, and constructing a state-action-reward set; the strategy is evaluated and updated on the basis of the collected state-action-reward data set, and then the energy management strategy is optimized. By fusing the variable component sub-circuit and the traditional neural network, efficient operation of the fuel cell system is ensured while the state of charge of the lithium battery is maintained in an ideal interval; and the gradient of the quantum circuit parameters is accurately calculated by using a parameter transfer rule, so that the optimization process of the quantum strategy learning energy management strategy is more accurate and efficient.
Owner:NORTHWESTERN POLYTECHNICAL UNIV +1

Electric energy meter production decision optimization method and system based on genetic algorithm

The invention relates to an electric energy meter production decision optimization method and system based on a genetic algorithm, and the method comprises the following steps: collecting and analyzing the system composition of an electric energy meter production line and main influence factors of the capacity of the electric energy meter production line, and constructing an evaluation index system of the capacity of the electric energy meter; performing expert evaluation based on the evaluation system of the production efficiency of the electric energy meter, and determining weight distribution of each evaluation index; constructing a multi-objective optimization model by taking optimal production efficiency and lowest production cost as optimization objectives; solving the multi-objective optimization model by utilizing a genetic algorithm to obtain an optimal electric energy meter production scheme, and realizing optimal sorting of the production scheme for decision makers to select; in the decision execution process, real-time data of the production process is continuously monitored, and when an abnormal condition occurs or an expected result is not met in the execution process, an early warning report is generated and self-adaptive adjustment is performed according to an actual condition, so that practical deployment of the optimized production decision is ensured.
Owner:FUJIAN NETPOWER TECH DEV CO LTD +1

IPv6 address generation method and device based on few-seed image coding

The invention relates to an IPv6 address generation method and device based on few-seed image coding, and belongs to the technical field of network security. The method comprises the following steps: preprocessing: extracting an active IPv6 address set of a few-seed area from collected active IPv6 addresses, and respectively constructing a graph structure and a coding vector for the set; extracting features; the method comprises the steps of active address generation, image generation, address generation and distributed detection, alias prefix detection and active IPv6 address detection are carried out through distributed detection, a result obtained through detection is subjected to preprocessing and feature extraction and then is sent to an image generation sub-module for fine adjustment, and after the operation is repeated for multiple times, the target of conversion rate is completed. According to the invention, a complex seed address configuration rule can be effectively learned, and the problem of low detection efficiency caused by sampling deviation is solved.
Owner:YUANHENG (JINAN) DIGITAL INTELLIGENCE TECHNOLOGY CO LTD

Multi-source software-defined science and education resource recommendation method and system based on knowledge graph

The invention provides a multi-source software-defined science and education resource recommendation method and system based on a knowledge graph, and the method comprises the steps: constructing an artificial intelligence knowledge graph based on the relation between artificial intelligence knowledge entities; obtaining science and education resource data of a science and education institution, extracting knowledge entities in the science and education resource data, and connecting the knowledge entities to the artificial intelligence knowledge graph to obtain a science and education resource knowledge graph; extracting local resource features / user features based on a graph neural network to obtain local resource features and user features of each client; constructing a local knowledge graph based on the science and education resource knowledge graph, and performing model training by taking the local resource features of each client as initial features until the model converges; and inputting the users and the resources into the graph neural network for prediction, and recommending the resources with high scores to each user. According to the scheme, the relationship between knowledge entities in the field of artificial intelligence is effectively extracted, a structured knowledge graph is formed, and the recommendation precision is improved.
Owner:XI AN JIAOTONG UNIV

Off-line reinforcement learning method combining generalized advantage estimation and mode decomposition interaction

The invention belongs to off-line reinforcement learning, and particularly relates to an off-line reinforcement learning method combining generalized advantage estimation and modal decomposition interaction. In order to solve the problems of insufficient track splicing capability and intra-modal interaction and inter-modal interaction of multi-modal information in a track in an off-line reinforcement learning method based on TransFormer, the track splicing capability of a model in an off-line data set is improved by adopting generalized advantage estimation, a modal decomposition interaction module utilizes an encoder-decoder structure, and a mode decomposition interaction module utilizes an encoder-decoder structure, so that the track splicing capability of the model in the off-line data set is improved. And the encoder effectively processes time sequence information in a single mode by utilizing modal internal interaction based on ConvFormer. Relative to this, the correlation between the state and the action is captured based on the interaction between the modes of the TransFormer, so that the characterization capability of the model on the state and action sequence is enhanced. The decoder further fuses multi-modal information by using convolution and cross-attention mechanisms, thereby realizing more accurate motion prediction.
Owner:ZHONGBEI UNIV

A personal thermal comfort prediction method and system

The present invention discloses a method and system for predicting personal thermal comfort, which belongs to the cross-technical field of artificial intelligence and building energy management. The method comprises: acquiring environmental data, personal physiological data, personal facial thermal imaging and personal thermal comfort feedback data and dividing them into a support set and a query set; inputting the data of the support set and the query set into a pre-trained deep neural network to obtain the personal thermal comfort level; the method of the present invention supports small sample learning, and has the advantages of low computational complexity and high prediction accuracy.
Owner:NANJING UNIV OF POSTS & TELECOMM

Touch and talk pen with AI interaction function

The utility model discloses a touch and talk pen with an AI interaction function, and belongs to the technical field of touch and talk pens. Comprising a touch and talk pen point, a touch and talk pen holder, a display screen, a touch and talk module installed in the touch and talk pen holder, and a loudspeaker, a microphone and a control button which are installed on the side wall of the touch and talk pen holder. Wherein the touch and talk module is connected with the display screen, the touch and talk pen, the loudspeaker, the microphone and the control button, and communicates with an external AI server. The touch and talk pen provided by the utility model has multimedia interaction capability, and can realize AI autonomous teaching and learning.
Owner:东莞市臻兴电子科技有限公司

Remote sensing landslide target detection model, method and system and readable medium

The invention relates to the technical field of remote sensing image target detection, in particular to a remote sensing landslide target detection model, method and system and a readable medium. According to the remote sensing landslide target detection model provided by the invention, firstly, an embedded layer, a position coding module and an attention feature extraction module are pre-trained on a first training set, and learning of knowledge attributes associated with an auxiliary image is realized; and then an attention feature extraction module and a Mask-RCNN model are further trained on a complete data set to realize fusion of knowledge features and visible light image features, the features of the landslide are comprehensively described, a deep learning model is adopted to automatically extract complex features, and the detection capability of the landslide area is improved.
Owner:HEFEI UNIV OF TECH

Information push method and system based on user behavior sequence

The present application provides an information push method and system based on user behavior sequence. First, by acquiring user interest learning tasks generated by a basic user behavior mining network, a progressive training process is used to perform user interest learning on the basic user behavior mining network, which can gradually improve the performance and stability of the network and ensure that the generated target user behavior mining network has higher quality; secondly, by monitoring the training results of the first progressive training process in a second progressive training node and performing user interest learning of the second progressive training process when the network parameters are stable, dynamic adjustment and optimization of the training process can be achieved, thereby improving training efficiency and effect; finally, by mining a user interest point map of a target user behavior sequence based on the target user behavior mining network, user interests can be grasped more accurately, and information push services that better meet users' needs can be provided to improve user experience.
Owner:CHENGDU LECHAOREN TECH CO LTD

A dual-arm manipulation task learning method and system based on a large model

The present invention discloses a dual-arm operation task learning method and system based on a large model, belonging to the field of neural network learning and robotics technology. The method includes receiving a task environment diagram and task description information for dual-arm operation, inputting the task environment diagram and task description information into a large visual language model, and decomposing them into a plurality of subtasks; determining a reward function according to the task description information, task perception space information and action space information corresponding to each subtask, and training based on a reinforcement learning model to construct a corresponding subtask model, and the subtask model is used to complete each subtask respectively; according to the operation sequence of a plurality of subtasks, calling a plurality of subtask models in sequence to perform dual-arm operation, and collecting a dual-arm trajectory data set, learning the dual-arm trajectory data set through an imitation learning algorithm, and obtaining a dual-arm operation strategy. The present invention realizes the learning of complex dual-arm operation tasks and improves the robustness of the operation strategy.
Owner:BEIJING MALIMAO TECHNOLOGY CO LTD

A quantitative data processing method based on cloud computing

The present invention discloses a quantitative data processing method based on cloud computing, which belongs to the technical field of cloud computing and quantitative data processing. By adopting a deep learning algorithm and a multi-level search algorithm to optimize the parameters of a quantitative data analysis model, the learning of historical data is realized, and rules that can process quantitative data are formed. The quantitative data are then processed according to the rules, thereby realizing automatic processing of quantitative data. This method can not only effectively improve the analysis efficiency of quantitative data, but also eliminate errors caused by human analysis.
Owner:SHENZHEN CENTURY FRONTIER QUANTITATIVE TECH CO LTD

Intelligent Internet of Things operating system and control method thereof

The invention relates to the field of intelligent Internet of Things, in particular to an intelligent Internet of Things operating system and a control method thereof.The intelligent Internet of Things operating system is provided with a plurality of image acquisition devices arranged in groups and comprises a shooting module used for shooting real-time images of a plurality of to-be-monitored points and generating corresponding image data, and a generation module used for filtering the image data and sending the filtered image data to a server; the filtering module is used for filtering the filtering data and generating corresponding filtering data and a shielding rate learning model, the learning module is used for preprocessing the filtering data, selecting a plurality of index characteristics for learning and generating a shielding rate distribution diagram of a real-time image, the alarm module is used for receiving the shielding rate distribution diagram and comparing the shielding rate distribution diagram with a shielding rate threshold value to generate a corresponding comparison result, and the object driving module is used for driving the object to move. The method and the device are used for adjusting the sheltering object of the to-be-monitored point according to the comparison result, the sheltering problem of the camera of the to-be-monitored point is solved to a certain extent, the problem that the image is not clear due to factors such as fog is reduced, the recognition accuracy of an Internet of Things operating system is improved, and the actual experience of a user is improved.
Owner:GUANGZHOU JIESHENG INFORMATION TECH

Multi-thread concurrent processing method and system based on adaptive entropy segmentation and interactive differential learning

The invention relates to the technical field of computer science, in particular to a multi-thread concurrent processing method and system based on adaptive entropy segmentation and interactive differential learning, and aims to dynamically divide preprocessed data through an adaptive entropy segmentation algorithm and optimize a data processing path by using an interactive differential learning algorithm. Finally, the system realizes the backtracking and correction of the abnormal data through a multi-level error correction backtracking mechanism, and ensures the consistency and accuracy of the final data. According to the method, the problems of non-uniform load, insufficient data processing path optimization and poor abnormal data processing in the traditional multi-thread concurrent processing are effectively solved, and the processing efficiency and data reliability of the system are greatly improved.
Owner:HUNAN BEIDOU SEG NAVIGATION TECH CO LTD

Method, medium and device based on AI agent and low-code generation model

The present invention is a method, medium and device for generating models based on AI agents and low-code, and relates to the field of data processing technology, including: building a target AI agent and configuring an output API interface format for the target AI agent, obtaining target demand data, inputting the target model data into a low-code platform, formatting the target model data based on the API interface format to generate candidate model fields, the low-code platform fills the generated candidate model fields into a graphical candidate model definition interface, and displays the target AI agent's related thinking process and attached reference documents and recommended questions, the target user determines the final model through the generated candidate model, it can be seen that the AI ​​agent is integrated with the low-code platform development, and interacts with the interface of the low-code platform and the AI ​​agent to realize the AI ​​agent's learning of the database and adaptation to the low-code platform, thereby improving the efficiency and accuracy of business model creation.
Owner:CHINA COMM INFORMATION TECH GRP CO LTD HANGZHOU BRANCH

Discrete probability prediction method and device based on conditional variation auto-encoder

The invention relates to a discrete probability prediction method and device based on a conditional variation auto-encoder, and the method comprises the steps: constructing a discrete probability power prediction model based on the conditional variation auto-encoder and a decoder; obtaining historical power data and historical candidate feature data of target new energy power generation to establish a new energy power generation training data set; training a discrete probability power prediction model based on the new energy power generation training data set to generate a new energy power generation prediction model, and predicting target new energy power generation distribution by using the new energy power generation prediction model; and inferring actual Bernoulli distribution corresponding to the preset Bernoulli distribution according to the enhanced inference strategy and the trained decoder. Therefore, the problems that in the prior art, the prediction time cost of new energy power generation is high, meanwhile, the probability distribution of new energy is difficult to accurately and efficiently predict, complex mixed distribution of photovoltaic power generation is ignored, and balance between continuous and discrete photovoltaic distribution is difficult to obtain are solved.
Owner:TSINGHUA UNIVERSITY

Method, medium and equipment based on AI agent and low-code generation model

The invention discloses a method, medium and equipment for generating a model based on an AI agent and a low code, and relates to the technical field of data processing, and the method comprises the steps: building a target AI agent, configuring an output API interface format for the target AI agent, obtaining target demand data, inputting target model data into a low-code platform, and outputting the target model data to the low-code platform; and performing formatting processing on the target model data based on an API interface format to generate candidate model fields, filling the generated candidate model fields into a graphical candidate model definition interface by a low-code platform, and displaying a related thinking process of the target AI agent and affiliated reference documents and recommendation problems. According to the method, the target user determines the final model through the generated candidate model, the AI agent and low-code platform development are fused, through interaction between the low-code platform and the interface of the AI agent, learning of the AI agent on the database and adaptation of the low-code platform are achieved, and the efficiency and accuracy of business model creation are improved.
Owner:CHINA COMM INFORMATION TECH GRP CO LTD HANGZHOU BRANCH

Hearing aid with multi-language automatic conversion function and hearing aid system

The invention provides a hearing aid with a multi-language automatic conversion function and a hearing aid system, and belongs to the technical field of hearing aids, the hearing aid is integrated with a multi-language recognition and conversion module, and language types in voice signals can be recognized and converted in real time. Meanwhile, the hearing aid is also provided with a language conversion module under a transparent dialogue link and a language translation module under a telephone link, and an intelligent control system is used for optimizing the accuracy and efficiency of language conversion. Through a knowledge distillation method, a translation model capable of being deployed on the hearing aid is distilled from an existing end-to-end speech translation model, and the multi-language automatic conversion function of the hearing aid is achieved. According to the hearing aid with the multi-language automatic conversion function and the hearing aid system, the limitation of an existing hearing aid in the aspect of cross-language communication is solved, and a user can easily cope with communication challenges in different language environments.
Owner:SHENZHEN BAILINGNIAO HEARING TECH CO LTD

Safe interaction method and device for federal training medical model, equipment and medium

The invention is suitable for the technical field of digital medical treatment, and particularly relates to a safe interaction method and device for a federal training medical model, equipment and a medium. According to the method, a server side and a client side register in the same block chain, the server side broadcasts the weight of a current global model obtained by the last round of training to the block chain, the client side updates and trains a local model according to the weight to obtain a trained local model, the updated model weight of the trained local model is broadcasted to the block chain, and the updated model weight of the trained local model is broadcasted to the block chain. And the server performs accuracy calculation on the updated model weight and updates the current global model by using the verification data to obtain the first accuracy and the current global model of the current round of training, obtains the reward distribution amount of the client according to the first accuracy, realizes federated learning of the model, limits the client on the basis of the reward in the block chain, and improves the user experience. The invention aims to reduce the influence of a client on federal learning by means of forgery aggressive data and the like in an interaction process and improve the application accuracy of a model in medical treatment.
Owner:PING AN TECH (SHENZHEN) CO LTD

A multimodal knowledge graph completion method based on neighborhood semantic enhancement

ActiveCN118966347BEnhance semantic expression abilityachieve learningBiological modelsKnowledge representationKnowledge graphSemantic feature
A multimodal knowledge graph completion method based on neighborhood semantic enhancement belongs to the field of multimodal knowledge graphs. Specifically, a neighborhood semantic enhancement module is first designed to fuse different neighborhood information into the representation of the central entity to enhance the semantic expression ability of the model. Then, the cross-modal attention mechanism is used to capture the interaction and common semantic features of information between different modalities to achieve the learning of neighborhood-guided features. Then, based on the contrastive learning method, the similarities and differences between positive and negative samples are compared to learn richer entity representations, and finally improve the multimodal knowledge graph completion results.
Owner:DALIAN UNIV OF TECH +1

A high-precision map dynamic detection and updating method using a general image restoration strategy

ActiveCN120472490BReduce build errorseasy to handle
The application discloses a high-precision map dynamic detection and updating method adopting a general image recovery strategy, belongs to the technical field of high-precision map dynamic detection and updating methods, and through a pre-training process, a degraded image is input into a network, features are extracted and enhanced layer by layer by adopting a feature generation module and a feature selection module, image recovery is realized by combining multi-dimensional feature fusion and a cross attention mechanism, the detail restoration and global consistency of the degraded image are improved, according to a BEV representation generated by the pre-training model in step S1, in combination with the historical state of the high-precision map, a dynamic detection module is adopted to identify elements that are newly added, deleted or unchanged in the map, and a difference map is output, according to the difference map generated in step S2, a map updating module is adopted to perform geometric adjustment and semantic correction on the marked added and deleted areas, an accurate and coherent local high-precision map is generated, and through a model evaluation framework, the performance of dynamic detection and map updating is comprehensively evaluated.
Owner:BEIHANG UNIV

A memristor neural network circuit simulating biological functions

The present invention relates to the technical field of memristor neural network circuits, and in particular to a memristor neural network circuit simulating biological functions, comprising a reward signal modulation module for converting an incentive signal; a first clue signal modulation module for converting a first clue signal; a second clue signal modulation module for converting a second clue signal; a first voltage control module and a first addition circuit for reconverting the converted incentive signal and the converted first clue signal; a second voltage control module and a first addition circuit for reconverting the converted incentive signal and the converted second clue signal; and by adjusting the incentive signal, the first clue signal and the second clue signal, functions such as learning, secondary learning, natural forgetting, artificial interference forgetting, generalization and differentiation in operant conditioning are realized. The present invention solves the problem that the existing circuit lacks a memristor neural network circuit with generalization and differentiation functions in an operant conditioning circuit.
Owner:CHANGZHOU UNIV

Video description method and system based on text quality perception

The present invention proposes a video description method and system based on text quality perception. The method first generates pseudo-truth value labels for all text descriptions of the same video annotation, and forms a vector representation of the quality of the text annotation by designing a text-label consistency evaluation method and a text-video similarity evaluation method; then obtains a description quality matrix containing batches of videos to ensure the existence of accurate, most comprehensive labels and least relevant labels, and through normalization, maps the quality values ​​corresponding to all evaluation indicators to the same scale to speed up the training of the model; finally, the normalized quality vector is used as an auxiliary signal, and is spliced ​​with the feature coding of the video to form a video feature expression of the annotation quality perception. By describing the quality-aware description decoding, the model can generate a description consistent with the quality. The present invention effectively learns from noisy data by comprehensively evaluating the quality of the description and text quality-aware description decoding.
Owner:JIANGXI UNIVERSITY OF FINANCE AND ECONOMICS

Feature mining method, recommendation method and related device and system

One or more embodiments of the invention provide a feature mining method, a recommendation method and a related device and system. By calling a preset large model, exploratory feature mining is performed on the original data based on a first mining prompt word under the condition that a target feature is not set by utilizing the understanding and reasoning capability of the preset large model for knowledge in each domain, and exploratory features are obtained; and performing validity analysis on the exploratory features to determine effective features. When exploratory feature mining is executed, conventional feature mining can be carried out based on the preset feature name list; and recording the effective features into a preset feature name list to realize online learning. The effectiveness analysis on the exploratory features comprises the steps of carrying out formal effectiveness analysis on feature formats, feature values and the like, and carrying out substantial effectiveness analysis on the basis of an offline AB experiment and an online AB experiment. The feature mining method provided by the embodiment of the invention can be realized based on an Agent architecture.
Owner:ALIPAY (HANGZHOU) INFORMATION TECH CO LTD

Plug-and-play license plate image automatic correction module suitable for open scene and training strategy of plug-and-play license plate image automatic correction module

The invention discloses a plug-and-play license plate image automatic correction module suitable for an open scene and a training strategy thereof. The license plate image automatic correction module comprises a license plate vertex offset regression subnet, a transformation matrix solving module, a grid generation module and an interpolation sampling module. The license plate vertex offset regression subnet is connected with a transformation matrix solving module, the transformation matrix solving module is connected with a grid generation module, and the grid generation module is connected with an interpolation sampling module; inputting a license plate image into a license plate vertex offset regression subnet and an interpolation sampling module; and the interpolation sampling module outputs the transformed license plate image to a license plate recognition network. The input license plate image can be geometrically corrected in a self-adaptive manner on the basis of the recognition accuracy; the license plate image automatic correction module has excellent performance when processing the license plate image with an improper shooting angle.
Owner:CHINA THREE GORGES UNIV

A hybrid energy storage system and method supporting mode switching

PendingCN122600190AAvoid frequent switchingachieve power
The application relates to the technical field of energy storage, and discloses a hybrid energy storage system and method supporting mode switching, which comprises a data acquisition and communication module, an operation state analysis and mode decision module, a switching trajectory planning and cooperative control module, a safety monitoring and dynamic compensation module, a panoramic instruction integration and execution module, and a strategy self-learning and optimization module; target operation mode instructions are generated by inputting comprehensive operation state characteristic data of the system into a pre-trained mode research and judgment neural network model, combining a pre-set hysteresis comparison strategy and a minimum time interval constraint of mode switching, and realizing research and judgment on multiple operation modes such as power smoothing, peak clipping and valley filling, frequency modulation auxiliary services, so that frequent mode switching caused by state fluctuations is avoided; characteristic data, control sequences and safety evaluation data of the whole switching process are recorded to form a history library, and the optimization of the switching strategy is realized.
Owner:SHENZHEN ENERGY BAODING POWER GENERATION CO LTD

Driving subject identification method and system in auxiliary driving environment

The invention discloses a driving subject identification method and system in an auxiliary driving environment. The method comprises the following steps: acquiring driving data of a vehicle; processing the acquired driving data, and screening lane changing time, steering wheel angle and acceleration fragment data; inputting the screened fragment data into a pre-constructed Stacking integrated driving subject recognition model, and recognizing the probabilities of driving subjects corresponding to different time periods in the fragment data; the Stacking integrated driving subject identification model comprises a primary learner and a secondary classifier, the primary learner comprises a lane changing working condition driving subject identification model and a steering working condition driving subject identification model, and the secondary classifier is a variable speed working condition driving subject identification model. According to the invention, the identification accuracy of the driving subject can be improved.
Owner:WUHAN UNIV OF TECH