59 results about "Knowledge resource" patented technology

The invention relates to the field of artificial intelligence, in particular to an intelligent standard knowledge retrieval system based on an AI large model, which comprises a standard knowledge management database, a multi-source acquisition preprocessing module, a semantic understanding and indexing module, an intelligent retrieval engine module, a knowledge enhancement module, a user interaction feedback module, a security control module and a deployment expansion module. The standard knowledge management database is used for storing standard knowledge design data, real-time retrieval data and feedback data and constructing a dynamically updated standard knowledge resource pool; through the multi-source standard knowledge acquisition and preprocessing module, multi-channel objective standard data can be integrated and dynamically updated, and the problem of knowledge fragmentation is solved; and through the semantic understanding and indexing module, industry professional semantic accurate matching is realized, the limitation of traditional keyword retrieval is broken through, and the accuracy and efficiency of standard knowledge retrieval are remarkably improved.

The invention discloses an industrial equipment after-sales intelligent auxiliary method and device, equipment and a storage medium, and the method comprises the steps: collecting equipment fault information inputted by a user, and converting the equipment fault information into a keyword set; obtaining multi-modal knowledge resources uploaded by a user, and labeling the multi-modal knowledge resources to generate a vector database containing semantic association; matching the keyword set with data in a vector database based on a retrieval enhancement generation mechanism to obtain knowledge fragments related to the equipment fault information; and calling a preset large language model to analyze the knowledge fragment to generate maintenance guidance content. According to the method, the multi-modal knowledge resources are converted into the vector database containing the semantic association, and the maintenance guidance content is generated for fault diagnosis of the equipment through the retrieval enhancement generation mechanism and the preset large language model, so that compared with the prior art, the equipment fault diagnosis efficiency and the response speed and accuracy of equipment maintenance are improved.

The invention provides a large model reasoning optimization method and system for operation and maintenance technical services, and the method comprises the steps: firstly obtaining a set comprising a plurality of to-be-processed operation and maintenance service requests, each to-be-processed operation and maintenance service request carrying operation and maintenance demand description information and an equipment operation scene identifier; performing priority dynamic calibration on operation and maintenance reasoning tasks based on the information, generating a priority list, deploying computing resources and operation and maintenance knowledge resources of large model reasoning according to the priority list and reasoning link requirements, forming a collaborative scheduling scheme, configuring a reasoning process according to the collaborative scheduling scheme, and executing large model reasoning; and finally, converting the result into an operation and maintenance response instruction in combination with the equipment operation scene identifier, and sending the operation and maintenance response instruction to the execution terminal, so that accurate processing of the operation and maintenance task, reasonable allocation of resources and efficient response of the operation and maintenance service are realized.

Disclosed herein are a system, method, and computer program product embodiments for retrieving and ranking knowledge resources relevant to a query from knowledge base(s). For example, a query for resources from knowledge base(s) may be received. Based on the query, a first set of candidate resources are obtained from the knowledge base(s) having a lexical similarity to the query search terms, and a second set of candidate resources are obtained from the knowledge base(s) having a semantical similarity to the search terms. For each of the first and second sets of candidate resources, a confidence level indicating the relevance of the candidate resource to the query is determined. The sets of candidate resources are ranked based on at least the confidence levels to generate a ranked list of candidate resources. A query response comprising at least a subset of the ranked list candidate resources is provided to a GUI.

The present disclosure relates to systems and methods for creating a copilot. The copilot uses plugins to provide additional features and functionalities to the copilot. The systems and methods use a large language model (LLM) pipeline to generate a knowledge resource used by the plugins and / or an LLM in the copilot to answer queries from a user.

The invention relates to the technical field of big data education, in particular to a big data teaching resource dynamic allocation practical training system based on AI self-learning, which comprises a teaching scene global data sensing module, a deep reinforcement learning decision core, a dynamic resource scheduling module and a practical training interaction environment layer, and the deep reinforcement learning decision core performs iterative updating on the double-layer resource scheduling model by continuously collecting user learning progress increment and system load change after resource allocation as reward feedback so as to realize collaborative dynamic allocation of computing hardware resources and teaching knowledge resources. The platform breaks the barrier between a traditional teaching system and a cloud computing base, achieves the simultaneous adjustment of computing power supply and teaching guidance according to the practical training progress, guarantees the smooth operation of a high-load task, reduces the operation cost through idle time capacity reduction, and achieves the collaborative optimization of soft and hard resources.

The invention discloses an animal nutrition and feed course resource sharing cloud platform and a knowledge graph construction method. The method comprises the steps of obtaining feeding knowledge resource data of different animal types and constructing a feeding knowledge meta-database; performing multi-granularity entity recognition and analysis on the feeding knowledge resources in the feeding knowledge meta-database to generate four types of entity sets, constructing an entity interaction graph, performing entity relationship reasoning to obtain a triple set, and constructing a feeding resource knowledge graph by using the triple set; constructing a personalized recommendation engine, carrying out user question answering and demand knowledge recommendation through the personalized recommendation engine, and carrying out interest resource recommendation based on user use behaviors; and building an animal nutrition and feed course resource sharing cloud platform by utilizing a micro-service architecture technology based on the personalized recommendation engine, the feeding knowledge meta-database and the feeding resource knowledge graph. Therefore, accurate, real-time and multi-dimensional knowledge service and help are provided for animal husbandry practitioners or interests and amateurs.

The invention discloses a multi-dimensional knowledge base management method and system associated with intelligent tags, and belongs to the technical field of knowledge base data management. Standard documents are analyzed through configuration rules, and semantic tags are generated; for non-standard documents and unstructured data, keywords are intelligently extracted according to the documents or user description to generate semantic tags; based on the knowledge element labels, a multi-dimensional knowledge graph is created, and intelligent association retrieval of the heterogeneous knowledge resources is achieved. According to the method, various documents can be managed in a unified manner, the human input in a knowledge base collection process is remarkably simplified, and the implementation cost is greatly reduced; and associated retrieval is supported, so that the efficiency and practicability of knowledge management are greatly improved.

The invention belongs to the technical field of intelligent education and personalized learning, and provides a personalized learning path recommendation method based on a course knowledge point sequence. The method aims at solving the problems that existing learning path recommendation logic association is insufficient, the personalized matching degree is low, and the optimization efficiency is not high. The method comprises the following steps: constructing a knowledge point sequence model by adopting a topological sorting algorithm on the basis of a curriculum knowledge point pre-modification and post-modification relationship, a difficulty level and dependence intensity, and generating a structured knowledge relationship graph; a learner feature model and a knowledge resource model are established, learner features are described from the dimensions of learning targets, cognitive levels, learning styles and the like, and the matching degree with knowledge points is calculated; and constructing an optimization model taking learning cost minimization, mastering degree maximization and path continuity optimization as targets, performing iterative optimization by using an improved intelligent optimization algorithm, and generating a learning path with logic rationality and personalized adaptability. According to the method, the scientificity and learning efficiency of learning path recommendation can be effectively improved.

A simulation method and related equipment for machining process training are disclosed. The method includes: acquiring engineering data and process data of the target workpiece; extracting features from the engineering data and combining them with the process data to construct a case resource library; performing semantic association analysis between the pre-set knowledge resource library and the machining cases in the case resource library to generate a process knowledge network; constructing a virtual training environment based on the process knowledge network; collecting interaction data of learners in the virtual training environment and evaluating the interaction data to obtain evaluation results; and generating guidance animations based on the evaluation results and the process knowledge network. This application can improve the learning efficiency of simulation training.

The invention discloses a network-on-chip debugging method and device, computer equipment and a storage medium, and relates to the technical field of integrated circuit design verification, and the method comprises the steps: generating network-on-chip data files in a preset file format, and generating a network-on-chip database containing network debugging information according to the files; acquiring target information corresponding to the network-on-chip debugging request from a network-on-chip database; and performing on-chip network debugging according to the target information, and writing a debugging result into an on-chip network database. The problem that NoC debugging is low in debugging efficiency and depends on verification of experiences of engineers can be solved. According to the method, the target information corresponding to the debugging request is provided for the user through the network-on-chip database, the dependence on the experience of a verification engineer is eliminated, the network-on-chip debugging difficulty is reduced, and the debugging efficiency is improved. All possible communication scenes and boundary conditions in the debugging process are covered through the target information, and the debugging coverage rate is increased. And continuously improving the database according to the debugging result to form knowledge resources.

1. Name of the product in this design: Artificial Intelligence Question-Answering Interactive Graphical User Interface for Electronic Devices. 2. Intended use of this design: for use in an electronic device. 3. The key design feature of this product is its graphical user interface. 4. The image or photograph that best illustrates the design's key features: the front view. 5. Purpose of the graphical user interface: This interface is used for AI question-and-answer interaction. Clicking "Knowledge Base Management" in the main view will take you to interface state diagram 1, where you can perform unified maintenance of the system's knowledge resources. Clicking "Quick Access Management" in interface state diagram 1 will take you to interface state diagram 2, where you can configure and maintain the system's quick access links.

This invention relates to a fault early warning system for hydro-generator units based on CEGD-FNN. The system includes: a feature extraction module for early fault signals of the hydro-generator unit, a fault diagnosis module for the hydro-generator unit, a status assessment module for the hydro-generator unit, a fault prediction module for the hydro-generator unit, and a human-machine interface module. These modules are sequentially connected. This invention employs a unified data platform integrating heterogeneous source information and a unified platform for open knowledge resource sharing. It can promptly obtain heterogeneous data from distributed systems and knowledge resources from different users, thereby achieving intelligent collaborative diagnosis of equipment faults and reducing losses caused by insufficient timely handling of emergency faults.

The invention provides a business processing method and system based on a large model and retrieval optimization, and the method comprises the steps: constructing a collection knowledge base, and carrying out the fine adjustment of a pre-trained large language model through a quantification low-rank adaptation technology, and obtaining a large language model for the collection business optimization. And a unique strategy of model parameter fixation and only low-rank matrix optimization is adopted in model training, so that the calculation resource occupation is greatly reduced, and the accuracy and performance of the large model in the collection professional field are remarkably improved. Furthermore, dynamic updating of collection related knowledge is achieved through application of the RAG technology, the problem of knowledge updating lag is effectively solved, the retrieval recall rate is remarkably increased through the synergistic effect of synonymous query enhancement and a mixed retrieval strategy, a large language model can accurately obtain related knowledge from a small amount of knowledge resources, and the retrieval efficiency is improved. Therefore, the accuracy and reliability of answering are greatly improved, more powerful support is provided for collection business processing, and the collection effect is effectively improved.

Disclosed herein are a system, method, and computer program product embodiments for recommending knowledge resources to resolve errors at a source and / or target system. For example, a request to post data to a target system is received from a source system. A determination is made that an error occurred with respect to the request. An error context for the error is determined. The error context comprises information describing the error and information describing the system. A representation of the error context is provided as an input to an ML model. The ML model is configured to predict a knowledge resource for resolving the error based on the error context. A prediction indicating the knowledge resource for resolving the error is received from the ML model. A recommendation to apply the knowledge resource on the source and / or target system is provided via a user interface based on the prediction.

The application discloses a kind of personal number knowledge base creation and configuration method supporting multi-dimension screening, it is related to data processing technical field, method includes: creating and the exclusive knowledge base of personal number binding, establish and the data interface connection of customer management system, communication push system;Configuration knowledge base basic function, establish file and the initial mapping of customer label, business scenario;Multi-dimension screening logic containing basic attribute, customer behavior, cross-system feedback dimension is built, preset screening dimension self-evolution process, business conflict calibration process and cross-system screening dimension generation process are handled;The process is executed to realize the real-time linkage of screening result and customer communication scene, multi-system, complete predictive screening and business process dynamic calibration.This method improves the adaptability and efficiency of knowledge resource screening, and provides support for personal number to efficiently carry out business.

This invention discloses an AI-based personalized workplace learning system and method for enterprises, comprising: an enterprise profile construction module, which collects multi-source data and constructs a digital profile of the enterprise through multimodal semantic analysis; a dynamic learning system generation module, which automatically generates a customized workplace learning system based on the enterprise profile using a large language model combined with thought chain and retrieval enhancement generation technology; a multimodal content extraction and AIGC production module, which reconstructs knowledge resources in its proprietary copyright content library into lightweight workplace knowledge units through a RAG and multi-agent collaborative architecture; and a personalized recommendation engine, which adopts an improved DSSM dual-tower model, introduces a dynamic attention feature cross-layer, and combines multi-source user features and enterprise context to achieve accurate push notifications. This invention achieves dynamic matching of the learning system with enterprise strategy, large-scale reconstruction of knowledge assets, and deep personalized recommendation, effectively solving the problems of rigid training systems and single recommendation dimensions in existing technologies.

The invention provides an intelligent decision and recommendation method based on an enterprise knowledge graph. According to the method, the enterprise knowledge graph covering multi-dimensional entities such as enterprise customers, products, supply chains, finance and employees and association relationships is constructed, and heterogeneous data dispersed in each business system in an enterprise is semantically integrated and associated to form a unified knowledge resource pool; the process can comprehensively and accurately reflect the internal relation among the entities in the enterprise operation process, and provides a complete and reliable data basis for subsequent decision analysis and recommendation. A multi-scene intelligent reasoning model is constructed based on an enterprise knowledge graph, and rich semantic association information in the knowledge graph can be utilized to perform deep mining and reasoning analysis on various data in an enterprise operation process.

The application provides a large language model driven open domain natural language reasoning question and answer system and method, a question rewriting module rewrites a user question into a rewritten question; a center calculation and management module manages calculation and knowledge resources of a large language model, and outputs the calculation and knowledge resources of the large language model required by a question core engine module to one or more sub-question and answer modules in a question and answer core engine module according to the type of the rewritten question; the question and answer core engine module reasons to obtain one or more candidate answers of the rewritten question and explainability information of the candidate answers according to the rewritten question and the calculation and knowledge resources of the large language model; and an aggregation reasoning module aggregates and reasons to obtain a final answer of the rewritten question and explainability information of the final answer according to the one or more candidate answers of the rewritten question and the explainability information of the candidate answers, and supports comprehensive question types, is easy to expand, is explainable, and has strong universality by using a large language model.

The application discloses a knowledge resource reliable protection method based on a consortium chain network, and comprises the following steps: an IPFS private network containing seven nodes is built, and an optimal storage node and a backup node are selected; a consortium chain network is established; based on an ERC-1155 standard, a non-fungible token for a knowledge resource file is established and stored in the consortium chain network, and a user is allowed to perform an operation on the non-fungible token, and meanwhile, non-fungible token data and transaction records generated by the operation are stored in nodes of the consortium chain network; all transaction records in the nodes of the consortium chain network are interacted with a public infrastructure network BSN. Therefore, the problem that the rights and interests of a user about a knowledge resource file are infringed is solved.

The invention relates to the technical field of large language models, and discloses a knowledge base questioning method and device, equipment and a storage medium, and the method comprises the steps: obtaining user question information; the user question information is input into a target model, a target knowledge base is referred to based on the user question information through the target model, corresponding answer information is generated and displayed, and the target model comprises at least one large model. By introducing the knowledge base, the large model answers the question information of the user by referring to the knowledge of the target knowledge base, and external knowledge resources are introduced into the reasoning process of the model, so that the mastering of the model on the knowledge in different fields can be effectively improved, and the accuracy and comprehensiveness of answering are further improved.

This application provides a method and system for optimizing large-scale model inference for operation and maintenance (O&M) technical services. First, a set of multiple pending O&M service requests is obtained. Each pending O&M service request carries O&M requirement description information and equipment operating scenario identifiers. Then, based on the above information, the O&M inference tasks are dynamically prioritized, generating a priority list. According to the priority list and inference link requirements, computational resources and O&M knowledge resources for large-scale model inference are allocated to form a collaborative scheduling scheme. The inference process is configured and executed according to the collaborative scheduling scheme, generating O&M inference results. Finally, the results are converted into O&M response instructions based on the equipment operating scenario identifiers and sent to the execution terminal. This achieves accurate processing of O&M tasks, reasonable resource allocation, and efficient response to O&M services.

The application discloses an automatic proposition method and system based on structural knowledge resources and reasoning track verification, and the method comprises the following steps: constructing structural knowledge resources for automatic proposition, and forming a double-layer representation of a task skeleton layer and a scene instance layer; receiving and analyzing proposition demand input by a teacher to obtain structured demand information, and compiling to obtain a teaching intention; extracting a task-related subgraph corresponding to a current proposition target from the structural knowledge resources according to the structured demand information; matching a target proposition mode template according to the task-related subgraph and constructing a task skeleton according to the target proposition mode template; planning a candidate reasoning track on the task skeleton, and outputting a verified reasoning track satisfying verification constraints; determining question face given information and hidden information around the verified reasoning track; mapping the task skeleton to a specific question scene, and jointly generating a title, an analysis and an answer based on the same underlying reasoning track. The application can improve the logical rigor of the automatic proposition result, the consistency of the question and the analysis answer.

The application provides an ontology agent autonomous evolution and knowledge updating method, device, equipment, medium and system based on continuous learning, wherein the method comprises the following steps: acquiring baseline configuration records, historical processing records and knowledge resource records of an ontology agent, the baseline configuration records comprising baseline version identification, prompt word constraint templates, replay task sets and fallback anchor points; generating a running evidence frame based on the historical processing records; determining a knowledge gap segment according to the running evidence frame and the knowledge resource records; converting the knowledge gap segment into a knowledge increment index, and generating a resource routing rewrite item according to the running evidence frame; generating a candidate evolution package according to the knowledge increment index and the resource routing rewrite item; loading the candidate evolution package into a shadow service container to obtain a candidate evolution version; calling the candidate evolution version to process the replay task set through a unified service interface, and generating a difference check record; and writing the configuration record to activate the agent when the difference check record meets the takeover condition.

The invention discloses a construction method of an engineering specification intelligent question-answering system oriented to pavement health management. Currently, knowledge processing in the field of road engineering faces the problems of tedious information retrieval, limited application of a large language model and the like, and an efficient question-answering system is urgently needed for intelligent road development. The system is built through the steps of data preprocessing, rewriting, retrieval optimization, model testing and the like. A BERT text filter screening problem is introduced, a road industry specification context is divided, a three-layer retrieval mechanism of a vector, a full text and a knowledge graph is constructed, and a basic large model and an RAG technology are applied. According to the method, efficient retrieval and quick response are achieved, the answer accuracy is improved, the data quality and retrieval efficiency are guaranteed, industry knowledge resources are integrated, the requirement of an intelligent highway for accurately obtaining industry specifications is met, and the problem of knowledge processing and intelligent interaction in the field of road engineering is effectively solved.

The application discloses a kind of military software defect multimodal knowledge graph construction method, device and system, belong to knowledge graph construction field, comprising: S1, mode layer design;S2, defect knowledge mining: data source is collected, information extraction and data preprocessing;S3, multimodal knowledge graph construction: data entry is carried out in multiple databases, the semantic relationship between nodes is stored in graph database, the multimodal information of graph database node is stored in relational database, and multimodal knowledge graph is constructed.The military software defect knowledge graph of the data driving and knowledge guiding combination constructed by the application changes the traditional knowledge management mode, multidirectional rich semantic information and the defect of other information are shown, the problems of military software defect knowledge resource fragmentation, insufficient utilization, high knowledge acquisition cost and updating difficulty are solved, and foundation is laid for military software defect encyclopedia retrieval, intelligent question and answer, intelligent prediction and intelligent recommendation and the like application.

The invention belongs to the technical field of process approval, and particularly relates to a knowledge-enhanced process approval system and method based on large model assistance. Comprising a data acquisition module, a knowledge base construction module, a large model integration module, a knowledge reasoning engine, an interactive interface and a log and feedback module. The data acquisition module collects and preprocesses various data in the approval process in the production management field and management files related to enterprise production management. The knowledge base construction module establishes a comprehensive multi-mode knowledge base which comprises various types of knowledge resources and carries out tagging processing on the resources in the knowledge base. The method has the beneficial effects that the key information in the approval process can be automatically analyzed, and the pre-trained large model is called to carry out related knowledge pushing, knowledge reasoning and decision suggestion, so that the approver is assisted to make a judgment quickly and accurately, and the approval efficiency of the process can be improved.

The invention discloses a multi-dimensional guiding type teaching assistance method and system based on retrieval enhancement, and the method comprises the steps: collecting questions, answers, practical operation feedback and historical data of students through a heuristic dialogue, recognizing and cognizing weak points, learning demands and question adaptability through a multi-dimensional analysis model, and constructing a personalized learning situation portrait. And on the basis of a large model and a portrait, personalized content adaptive to a teaching scene is customized, a multi-source knowledge resource library traceability identifier is embedded, and the content is ensured to be traceable and accurate through cross validation. Through a visual carrier, multi-round interaction is carried out through'stepped questioning + scene example ', dynamic feedback is collected, and a teaching strategy is optimized. And finally, giving a comprehensive score of a learning result of the student from three-dimensional quantitative evaluation of learning condition positioning accuracy, content generation suitability and guide interaction effectiveness, and improving teaching quality and learning efficiency.

The invention relates to a semi-physical simulation testing method for embedded software, belongs to the technical field of embedded software testing, and solves the problems of low efficiency, poor accuracy, incapability of supporting reuse and unreasonable configuration in obtaining a test case in an embedded software semi-physical simulation test in the prior art. Comprising the following steps: acquiring a hardware resource demand set of to-be-tested embedded software, acquiring a test case set of the hardware resource demand set based on a historical knowledge resource database, performing dependency relationship identification on the test case set to obtain an optimized case set, and processing the optimized case set based on a coding control instruction to obtain the to-be-tested embedded software. And optimizing the use case set to obtain a coding control instruction set corresponding to the optimized use case set, constructing an automatic test script based on the optimized use case set and the coding control instruction set, and realizing the semi-physical simulation test of the embedded software to be tested based on the automatic test script. The embedded software semi-physical simulation test method which is efficient and accurate, supports reuse and is reasonable in configuration is achieved.