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

529results about How to "Improve build efficiency" patented technology

Text robot application system based on large model

The invention discloses a text robot application system based on a large model, and the system comprises the following modules: a knowledge base and analysis module which receives and processes a business document, decomposes the content into semantic units, and marks context features; the question-answer generation module automatically generates question-answer pairs through deep semantic analysis and stores the question-answer pairs in a vector database; the question extension module is used for dynamically extending similar questions by using a natural language generation technology; the semantic intention analysis module is used for accurately extracting a problem core intention through context semantic analysis and mapping the problem core intention to a service path; the text workflow management module is used for realizing dynamic routing of multiple service scenes by adopting a logic tree model; the context semantic association module is used for analyzing and optimizing problem expression through multiple rounds of dialogues; the bottom response module is used for providing multi-level answers in combination with a question and answer database, document recall and dynamic generation; and the intelligent learning module records unsolved problems and optimizes the question and answer library and semantic rules through a learning algorithm.
Owner:KEXUN JIALIAN INFORMATION TECH CO LTD

Instruction fine tuning data set construction method and device

The invention belongs to the technical field of data set construction, and discloses an instruction fine-tuning data set construction method and device, and the method comprises the steps: constructing an original instruction fine-tuning data set through a context prompt learning method based on a thinking chain by employing a given semi-structured data set of a certain field; samples are extracted from the original instruction fine adjustment data set to preliminarily train the basic large language model, and a brief pre-experience large language model is obtained; and performing quality evaluation on all question and answer pairs in the original instruction fine-tuning data set by using a brief pre-experience large language model, and screening and optimizing the original instruction fine-tuning data set based on a quality evaluation result to obtain a final instruction fine-tuning data set. Agile and high-quality construction of knowledge question and answer data is realized through three steps of generation of an original question and answer fine adjustment data set, pre-experience large language model training and question and answer pair quality evaluation. The construction efficiency of instruction fine adjustment data can be effectively improved, and meanwhile the data quality is guaranteed.
Owner:MILITARY SCI INFORMATION RES CENT ACAD OF MILITARY SCI OF THE CHINESE PEOPLES LIBERATION ARMY

Nursing corpus automatic creation method based on knowledge graph

The invention discloses a knowledge graph-based nursing corpus automatic creation method, and relates to the field of artificial intelligence technology and medical information processing, and the method comprises a multi-dimensional data acquisition stage, a knowledge graph construction stage, a corpus automatic generation and updating stage, and a corpus quality control and evaluation stage. According to the automatic corpus generation method driven by the knowledge graph, dynamic generation and real-time updating of corpora are achieved by constructing an ontology structure, a corpus generation template and an updating algorithm in the nursing field; through a deep learning model and a transfer learning technology, new nursing knowledge and a diversified information structure are continuously introduced into the corpus, and the diversity of corpus content is increased.
Owner:CHONGQING MEDICAL UNIVERSITY

Digital twinborn scene construction method based on AI native and related device

The invention discloses an AI native-based digital twinborn scene construction method and a related device, relates to the technical field of software, and is applied to a large language model to acquire input information for a target digital twinborn scene and perform intention recognition on the input information. If the intention recognition result of the input information contains the target orientation, determining a target business process for realizing the target orientation; and function calling of the API function is carried out according to the target business process so as to realize target guidance in the target digital twinning scene. According to the method, digital twinning scene construction is carried out based on the AI native thought, and target-oriented autonomous completion of business process arrangement and function calling is supported, so that the product scene construction efficiency can be greatly improved.
Owner:HANGZHOU ZHONGBO SOFTWARE TECH CO LTD

Fluororubber field knowledge graph construction method based on large language model

The invention provides a fluororubber field knowledge graph construction method based on a large language model, and the method comprises the steps: obtaining process related knowledge data of the fluororubber field, and carrying out the classification, and obtaining the classification knowledge data of the fluororubber field; based on a preset ChatGLM model, performing knowledge extraction according to the fluororubber field classification knowledge data to extract key entities and relationships; carrying out deep analysis on the key entity and the relationship by utilizing semantic correlation and context association analysis, and enhancing the connectivity of the key entity and knowledge in the relationship through semantic similarity and association strength to obtain fused knowledge data; explaining and expanding the fused knowledge data by using a ChatGLM model to obtain expanded triple data; and performing knowledge fusion on the triple data, and performing graph storage by using a Neo4j database to obtain a knowledge graph. According to the method, the knowledge graph construction efficiency is remarkably improved through automatic knowledge extraction and processing of the large language model, and the time cost of manual labeling and data processing is reduced.
Owner:SICHUAN UNIVERSITY OF SCIENCE AND ENGINEERING +1

Power emergency unstructured document directory construction method and device, computer equipment, storage medium and computer program product

The invention relates to an electric power emergency unstructured document directory construction method and device, computer equipment, a storage medium and a computer program product. The method comprises the steps of obtaining a to-be-processed power emergency unstructured document; according to the to-be-processed power emergency unstructured document and the keywords in the to-be-processed power emergency unstructured document, obtaining title information of each chapter of the to-be-processed power emergency unstructured document; determining a target word vector corresponding to the title information of each chapter according to the title information of each chapter and the text information under the title information of each chapter; according to the target word vector corresponding to the title information of each chapter, determining a hierarchical relationship between the title information of each chapter; and according to the title information of each chapter and the hierarchical relationship between the title information of each chapter, constructing directory information corresponding to the to-be-processed power emergency unstructured document. By adopting the method, the construction efficiency of the power emergency unstructured document directory can be improved.
Owner:GUANGDONG POWER GRID CO LTD

Process industry text knowledge extraction data set automatic construction method and system

The invention belongs to but not limited to the technical field of text extraction, and particularly relates to an automatic construction method and system for a process industry text knowledge extraction dataset. Firstly, based on a word segmentation tool and a TF-IDF algorithm, an unlabeled text in the process industry field is converted into a large language model fine tuning dataset, and a large language model is subjected to fine tuning; the system has specific knowledge of the field; then, generating an initial knowledge extraction sample set with confidence through multi-stage exploration-utilization ratio adjustment based on the fine-tuned large language model; and finally, through a confidence-based large-scale sample set error detection and correction method, obtaining a sample data set which is finally used for domain knowledge extraction model training. Through the low-cost and high-efficiency industrial text knowledge extraction sample set construction and application method, the input-output ratio of resources is increased to the maximum extent, and the construction and application efficiency of an industrial safety knowledge extraction algorithm is improved.
Owner:HUAZHONG UNIV OF SCI & TECH

Tumor whole course intelligent management platform and method

The invention discloses a tumor whole course intelligent management platform and method, and particularly relates to the technical field of medical model management. Carrying out semantic analysis and uniform format processing on the multi-modal data from different sources by utilizing a natural language processing technology and a standardized tool; using a feature selection algorithm to screen key features related to tumor types and treatment schemes; through analyzing mutual information of the key features and the target variables and mutual information among the key features, evaluating the degree of redundant hidden dangers existing in the screened key features; the semantic consistency of the multi-modal data from different sources is evaluated by comparing and analyzing the prediction label and the actual label of the multi-modal data; and comprehensively analyzing the redundant hidden danger degree of the screened key features and the semantic consistency of the multi-modal data from different sources, and judging whether the personalized treatment effect prediction model can be constructed or not.
Owner:JILIN UNIVERSITY

Electric power knowledge graph construction method and system based on active learning

The invention discloses an active learning-based electric power knowledge graph construction method and system, and relates to the technical field of electric power market transaction data analysis, and the method comprises the steps: collecting data, cleaning the collected data, generating word prediction task data of an electric power transaction scene, and training an electric power field word embedding model; generating an entity relationship training sample, inputting a word embedding model, performing entity relationship label prediction through an entity relationship joint extraction model, extracting a high-quality sample based on active learning to perform part-of-speech tagging, and training the model based on a tagged sample; and applying the trained entity relationship joint extraction model to power transaction data to construct a knowledge graph, performing manual correction and entity unification, and storing the knowledge graph into a Neo4j database. According to the method, active learning and deep learning are combined, so that the sample labeling cost is effectively reduced, and meanwhile, the model performance is ensured.
Owner:GUANGXI POWER GRID CORP

Power system vector knowledge base construction method based on text vectorization

The invention relates to a power system vector knowledge base construction method based on text vectorization, which comprises the following steps of: S1, acquiring data original texts and metadata related to construction of a power system vector knowledge base, and preprocessing the data original texts and the metadata; s2, text vectorization is carried out through a sparse vector and dense vector combination method; s3, storing the original text and the metadata in a relational database, storing the vector data in an NoSQL vector database, and constructing an association relationship; s4, when a user inputs a query, performing optimization processing on a query vector, improving a query algorithm and optimizing a query process, and introducing a multi-stage screening mechanism to obtain a preliminary retrieval result; and S5, based on an enhanced recall strategy, reordering the preliminary retrieval results by using domain-specific information and rules to obtain a final retrieval result. The construction efficiency and the use effect of the power system knowledge base can be effectively improved.
Owner:STATE GRID INFO TELECOM GREAT POWER SCI & TECH

Collaborative design system based on BIM technology

The invention relates to the technical field of BIM (Building Information Modeling) design, solves the problems of asymmetric post layer information, non-uniform drawing specification in specialties, many changes among specialties and difficulty in collaboration in the existing BIM design process, and discloses a collaborative design system based on a BIM technology, which comprises a cloud platform and a design end connected with the cloud platform, the cloud end comprises a project creation module, a file management module, a collaborative design mode selection module, a three-dimensional collaborative design module and a data providing management module, and the design end comprises a design module, a data providing module, a collision detection module and a collaborative punching module. According to the invention, rapid collaboration in each specialty is realized, the efficiency of model construction is effectively improved, and the flow of information provision is simplified.
Owner:中铁二院华东勘察设计有限责任公司

Low-code platform automatic construction and deployment system based on artificial intelligence

The invention discloses a low-code platform automatic construction and deployment system based on artificial intelligence. The system comprises a demand analysis module, a design module, a coding module, a construction module, a deployment module and a monitoring module. The working process of the system is as follows: a user inputs a demand description through a visual interface, and the system converts a demand into a standardized description through a demand analysis module; and the design module automatically generates a design scheme according to the demand description. The coding module generates source codes according to the design scheme, and the construction module compiles and packs the source codes; the test module automatically tests the software product to ensure the quality; the deployment module deploys a software product to a server, the monitoring module performs real-time monitoring and early warning, the system supports various programming languages and development frameworks, meets the requirements of different projects, and realizes comprehensive automation of software development by integrating a plurality of modules such as demand analysis, design, coding, construction, test, deployment and monitoring. And the whole process from user input demand to software online operation does not need excessive manual intervention, so that the development efficiency is greatly improved.
Owner:白晗熙 +1

Ancient book text entity relationship extraction method and system based on deep learning

The invention provides an ancient book text entity relationship extraction method and system based on deep learning, relates to the technical field of ancient book recognition processing, and aims to improve the accuracy and efficiency of ancient book text processing. The system realizes accurate recognition and extraction of entities and relationships thereof in ancient books and texts by fusing multi-modal information (characters and illustrations), a self-attention mechanism, a graph neural network and a dynamic knowledge graph technology. According to the method, the complex grammatical structure of classical Chinese in the ancient books is effectively processed, and capturing of the long-distance dependency relationship is ensured. By constructing and updating the knowledge graph in real time, the system greatly improves the efficiency of knowledge management. According to the technology, manual intervention is reduced, automation and large-scale application of ancient book processing are achieved, and protection of cultural heritage and development of academic research are promoted.
Owner:时代新媒体出版社有限责任公司

Industrial knowledge generation type decision-making method based on multi-granularity semantics and large model assistance

The invention discloses an industrial knowledge generation type decision-making method based on multi-granularity semantics and large model assistance. The method comprises the following steps of 1, encoding a business problem into a high-dimensional problem semantic feature; 2, processing the multi-modal industrial knowledge graph by utilizing entity links; based on TOP-K path expansion, obtaining different sub-graphs; 3, capturing different granularity features in the sub-graphs by adopting a graph neural network GNN to obtain industrial knowledge multi-granularity semantic features; 4, performing unified fusion on the industrial knowledge multi-granularity semantic features and the problem semantic features by using a GCN (Graph Convolutional Network); 5, constructing a triple sampling process based on SPARQL writing query, and extracting related triple data; 6, rewriting the structured triple data into a free format text, and constructing a problem-decision pair data set; and 7, performing fine adjustment on the large language model based on the problem-decision pair data set to obtain a knowledge text enhanced industrial knowledge generation type decision model.
Owner:CHONGQING UNIV

Data construction method, code question-answering method, task platform and code question-answering system

The embodiment of the invention provides a data construction method, a code question-answering method, a task platform and a code question-answering system. The data construction method comprises the steps of obtaining a first code snippet and an initial sample question for the first code snippet; rewriting the initial sample problem by using a text processing model and taking directory structure information of a sample code warehouse in the code library as context information to obtain a sample problem; based on the first code snippets and the sample questions, recalling related second code snippets from a code library; the text processing model is utilized, the second code snippets serve as context information, sample answers corresponding to the sample questions are generated, the sample questions and the sample answers are sample data used for training a code question and answer model, and the code question and answer model is suitable for a code warehouse. The data construction efficiency is improved, the data construction cost is reduced, the model obtained through training is adaptive to the code warehouse, and the user experience is improved.
Owner:ALIBABA (CHINA) CO LTD

Lake wetland migrant bird habitat inversion and optimization regulation and control method based on remote sensing

PendingCN119066341AImprove build efficiencyFast and accurate analysis
The invention discloses a lake wetland migrant bird habitat inversion and optimization regulation and control method based on remote sensing, and the method comprises the steps: obtaining wetland water and vegetation succession feature data, and carrying out the data preprocessing; extracting a water body area by adopting a normalized difference water body index method; the vegetation coverage of the lake wetland is extracted through a pixel bisection method; classifying land utilization types by adopting a random forest supervision classification method; analyzing the change rule of the population number and community structure of the lake wetland overwinter migrant birds; the method is used for quantifying and analyzing the influence of the current rapidly changing environment on the migrant birds and other wetland organisms, and the optimal threshold value suitable for the habitat of the migrant birds can be obtained.
Owner:NORTH CHINA ELECTRIC POWER UNIV

Knowledge graph construction method and device based on artificial intelligence, equipment and medium

The invention belongs to the field of artificial intelligence and the field of financial science and technology, and relates to a knowledge graph construction method and device based on artificial intelligence, computer equipment and a storage medium. Performing preprocessing to obtain an insurance knowledge text; performing entity extraction on the insurance knowledge text based on an entity extraction model to obtain an insurance entity; performing attribute extraction on the insurance knowledge text and the insurance entity based on an entity attribute extraction model to obtain an attribute value of the insurance entity; performing relation extraction on the insurance knowledge text based on a relation extraction model to obtain an insurance relation; based on the entity link model, performing data mapping processing on the ontology model by using the insurance entity, the attribute value of the insurance entity and the insurance relationship to obtain a mapping result; and performing knowledge storage processing on the mapping result based on the graph database to obtain a target knowledge graph. In addition, the target knowledge graph may be stored in a blockchain. According to the invention, the construction efficiency and the construction accuracy of the knowledge graph are improved.
Owner:CHINA PING AN PROPERTY INSURANCE CO LTD

Active load shedding optimization control method, system and device for wind power plant and storage medium

The invention provides an active load shedding optimization control method, system and device of a wind power plant and a storage medium, and belongs to the technical field of active power control of the wind power plant, and the method comprises the steps: constructing and training an SAC intelligent agent through an SAC algorithm; acquiring a wind power plant state quantity; inputting the state quantity of the wind power plant into the SAC intelligent agent to obtain a vector # imgabs0 # composed of active power initial reference values of all wind turbine generators; inputting the # imgabs 1 # into a constraint controller for secondary calculation to obtain a vector # imgabs 2 # composed of active power optimization reference values of the wind turbine generators; the wind power plant executes # imgabs3 #; and repeating the steps, and adjusting the active power of each wind turbine generator in real time. The model is high in generalization, stability, reliability and learning efficiency, real-time online calculation of the equivalent fatigue load can be achieved, reasonable distribution of the active power of the wind power plant can be achieved under the condition that the active power constraint of the wind power plant is met, the equivalent fatigue load of the whole wind power plant can be reduced, and the maintenance cost can be reduced.
Owner:SHANDONG UNIV

Monitoring network construction information processing method and device, terminal and medium

The invention discloses a monitoring network construction information processing method and device, a terminal and a medium, and the method comprises the steps: obtaining the video image information and equipment basic information of camera equipment based on the camera equipment which is accessed to a video platform; the method comprises the following steps: acquiring information of a camera device, determining GIS information and an actual coverage range of the camera device according to the acquired information, determining monitoring network planning auxiliary information based on a target monitoring area in which a monitoring network needs to be planned, combining the GIS information and the actual coverage range and according to a maximum coverage site selection problem logic, and determining the monitoring network planning auxiliary information based on the acquired monitoring network planning auxiliary information. The monitoring network construction of the target monitoring area is completed, the intelligent construction of the area monitoring network is realized, the monitoring video information is used, the dependence on extra non-monitoring structured information is reduced, the dependence on manual data processing is reduced, and the construction efficiency of the monitoring network is improved.
Owner:E SURFING VISION TECHNOLOGY CO LTD

Python project mirror image construction method and device, equipment and storage medium

The invention relates to the field of containers, and discloses a Python project mirror image construction method, device and equipment and a storage medium, and the method is used for constructing a Python project mirror image by adopting a multi-stage construction strategy so as to reduce the size of the mirror image. The method comprises the following steps: acquiring a first lightweight basic mirror image as a construction stage basic mirror image, and installing a basic dependency item and a construction tool; copying a dependency file in the Python project into the basic mirror image in the construction stage, and generating a dependency layer in combination with a construction tool; copying a code in the Python project into the basic mirror image in the construction stage, and executing a construction step in the code to obtain a construction product; obtaining a second lightweight basic mirror image as a running environment basic mirror image, and copying the dependency layer and the construction product into the running environment basic mirror image to obtain an initial mirror image; and performing compatibility verification on the initial mirror image, and using the initial mirror image passing the verification as a Python item mirror image.
Owner:SHANGHAI DONGPU INFORMATION TECH CO LTD

Age minimization method for data distribution information of Internet of Vehicles

The invention relates to an Internet of Vehicles data distribution information age minimization method, which obtains a near-end optimization model through training in advance, and executes information age updating and unmanned aerial vehicle track selection through a base station and the model in the Internet of Vehicles, so that the calculation and decision burden of an unmanned aerial vehicle can be reduced, and the unmanned aerial vehicle is enabled to mainly focus on physical movement and communication tasks; therefore, the energy efficiency and the task execution effect of the unmanned aerial vehicle are improved, and the base station, as a central control node, can collect and process the state information of the whole network so as to make a global optimal decision.
Owner:NINGBO UNIV

Establishment method and device of OPC (Optical Proximity Correction) model, optical proximity correction method and equipment, and storage medium

The invention discloses an OPC model establishing method and device, an optical proximity correction method and equipment and a readable storage medium, and the method comprises the steps: forming a semiconductor structure which is provided with a graphical photoresist; according to the semiconductor structure, obtaining the contour of a pattern in the patterned photoresist; measuring the contour of the pattern in the patterned photoresist to obtain a contour measurement value; and establishing an OPC model according to the contour measurement value. Compared with the measurement data after development obtained by directly measuring the pattern of the patterned photoresist, the technical scheme of the invention can effectively improve the measurement precision and obtain the high-precision profile measurement value, thereby effectively reducing the error of the established OPC model, facilitating the improvement of the establishment efficiency of the OPC model, and reducing the cost of the OPC model. And the correction precision of the optical proximity correction method can be improved.
Owner:ZHEJIANG ICSPROUT SEMICONDUCTOR CO LTD

Dark-induced enhanced luminescence expression vector as well as construction method and application thereof

The invention discloses a darkness-induced enhanced luminescence expression vector as well as a construction method and application thereof, and the enhanced luminescence expression vector is constructed by taking a vector pDES as a skeleton vector. A core element formed by sequentially connecting a promoter PsDIN6, a mutated nnLuz gene mnnLuz, a HisspS gene of neon lamp bacteria, an H3H gene, a CPH gene and an NPGA gene of aspergillus nidulans is inserted between an attR1 element and an attR2 element of a vector pDES from the 5'end to the 3 'end, and the vector is obtained. A luciferase Luz gene of luminous fungus neon lamp bacteria is subjected to random mutation by using a directed evolution technology, a luciferase mutant gene mLuz of which the luminous efficiency is 5.7 times higher than the original luminous efficiency is obtained through screening, and an expression vector constructed by the luciferase mutant gene mLuz is instantaneously expressed on tobacco leaves, so that the tobacco leaves do not emit light in daytime and emit bright fluorescence in darkness.
Owner:成都市花木技术服务中心 +2

Construction method and system for digital twinborn model of port production elements

The invention provides a construction method and system for a digital twin model of port production elements, and the method comprises the steps: determining a multi-dimensional model of each production element according to the information of the port production elements; determining a data model according to a data mapping relationship between the data acquired by each production element of the port and the multi-dimensional model of each production element; performing association fusion processing on the data model and the multi-dimensional model, and determining a port production element digital twin model; according to the information of the port production elements, constructing a parameterized template oriented to a digital twinborn model of the port production elements; and through a predefined interface template of the parameterization template, updating a model state of the digital twinborn model of the port production elements, and determining a customized digital twinborn model of the port production elements. According to the invention, a general modeling rule and a modular modeling method for a port application scene are formed, and the construction efficiency of the digital twinborn model is improved.
Owner:SHANGHAI JIAOTONG UNIV +2

Intelligent water affair light application rapid building system based on modularization

The invention relates to the technical field of water affair management, and discloses a modularization-based intelligent water affair light application rapid building system, which comprises a template library management module, which is used for storing and managing a plurality of preset function templates, and each function template is used for executing a specific function in water affair management; the parameter configuration module communicates with the template library management module and is used for performing parameterization configuration on the selected function template according to user requirements, and the parameterization configuration comprises data source configuration, operation parameter setting and output option selection; and the system combination and deployment module is used for combining the function templates subjected to parameterization configuration into a complete application system, and deploying the application system into a running environment through a containerization technology and a Kubernetes arrangement tool. Through modular design and template library management, the system can be rapidly configured and deployed according to different water affair management requirements, the construction time of the system is greatly shortened, and the system adapts to rapidly changing business requirements.
Owner:CHONGQING ZHONGDI INFORMATION TECHNOLOGY CO LTD

Mine geological drilling three-dimensional visualization method based on deep learning

The invention relates to the technical field of surveying and mapping, and discloses a mine geological drilling three-dimensional visualization method based on deep learning, which comprises the following steps: S1, collecting drilling data, and extracting drilling sampling site data from the drilling data by adopting a three-point positioning method; s2, preprocessing the collected data to form a data set for model training; s3, constructing a three-dimensional deep learning model; s4, training the three-dimensional deep learning model by using the data set to realize optimization operation on the three-dimensional deep learning model; s5, performing data drilling by using the optimized three-dimensional deep learning model to form and generate a three-dimensional geologic model; and S6, inputting the three-dimensional geologic model after drilling into visual equipment, and carrying out display operation on the three-dimensional geologic model. According to the invention, efficient processing and three-dimensional visual display of mine geological drilling data are realized, the efficiency of mine exploration and development is improved, the safety risk is reduced, and powerful support is provided for decision making of mining companies.
Owner:UNIV OF SCI & TECH LIAONING

Knowledge sharing method and system based on block chain and knowledge graph

The invention relates to the field of data processing, and discloses a knowledge sharing method and system based on a block chain and a knowledge graph, and the method comprises the following steps: carrying out the field division of a newly-added knowledge graph through an intelligent contract, and integrating the divided knowledge graph into a knowledge graph of a corresponding field, when a reasoning request of the smart contract is received, requesting an external reasoning service independent of the block chain through an oracle machine; the external reasoning service receives an oracle machine request, reasones and perfects a knowledge graph of the field by adopting a large language model, and transmits a reasoning result back to the intelligent contract; the external reasoning is used for mining potential rules in the knowledge graph through a prompt template, screening out a final logic rule through a scoring mechanism, and applying the logic rule to reasoning of the knowledge graph; and the smart contract receives the reasoning result and updates the knowledge graph of the field on the block chain. The application value of the knowledge graph is improved, the data security is improved, and the knowledge sharing requirements of different industries and fields can be met.
Owner:HUAQIAO UNIVERSITY

Intelligent substation virtual loop checking rule base construction method and system

According to the intelligent substation virtual circuit checking rule base construction method and system provided by the invention, the intelligent substation virtual circuit checking rule base is quickly constructed through sample learning, the risk of incorrect protection action caused by virtual circuit errors is reduced, and the safety and stability of a power grid are improved; the intelligent substation virtual circuit checking rule base construction method comprises the following steps: step 1, creating an intelligent substation virtual circuit checking rule model; step 2, acquiring an intelligent substation configuration file sample; 3, analyzing a configuration file sample of the intelligent substation, and extracting a relation topology; 4, searching whether the extracted attribute tag and the relation topology exist or not, and returning a search result; 5, if the retrieval result responds, rule creation is not carried out; step 6, if the retrieval result is not responded, checking by an expert; and step 7, instantiating the secondary equipment entity virtual loop checking rule model of which the retrieval result does not respond to the secondary equipment entity virtual loop checking rule model, and generating a virtual loop checking rule.
Owner:ELECTRIC POWER SCI RES INST OF STATE GRID XINJIANG ELECTRIC POWER CO LTD

Three-dimensional model reconstruction method, device, equipment and storage medium

The present application discloses a method, device, equipment and storage medium for reconstructing a three-dimensional model, the method comprising: performing multi-directional image acquisition on an object to be reconstructed to obtain a plurality of images of the object to be reconstructed; inputting each of the images of the object to be reconstructed into a trained de-reflection model for de-reflection processing to obtain a plurality of de-reflection reconstructed object images; wherein the de-reflection model performs multiple down-sampling and multiple up-sampling on the input image in sequence, and fuses the result of each up-sampling and the input image through channel splicing and transposed convolution to obtain a de-reflection image; performing de-occlusion processing on the occluded area of ​​each de-reflection reconstructed object image based on the occlusion mask map of the occluded area in each de-reflection reconstructed object image through a pre-trained de-occlusion model to obtain a plurality of processed reconstructed object images; performing three-dimensional reconstruction using each of the processed reconstructed object images to obtain a three-dimensional model of the object to be reconstructed.
Owner:HUNAN HAPPLY SUNSHINE INTERACTIVE ENTERTAINMENT MEDIA CO LTD

Channel establishment method and device and first terminal

The embodiment of the invention relates to the technical field of communication, in particular to a channel establishment method and device and a first terminal. The method comprises the following steps: under the condition that a channel establishment request initiated by a first application is obtained, executing a channel establishment method in an SDK (Software Development Kit) to obtain establishment parameter information required for establishing a data channel; sending the creation parameter information to a background service to indicate the background service to interact with an IMS protocol stack in the first terminal according to the creation parameter information, and constructing a data channel between the first terminal and a second application of the second terminal; the first application and the second application are the same application.
Owner:CHINA TELECOM CORP LTD TECHNOLOGY INNOVATION CENTER +1