2378 results about "Relevant information" patented technology

A user provides a question to be answered from detailed, dense or otherwise complex documents to a processing system that converts the question to a structured query language query and generates an embedding from the question, augmented by temporal data, synopses, themes, or other relevant information or data. The embedding is compared to embeddings generated from documents of a knowledge base to identify documents that are relevant to the question, and to rank such documents for their relevance. Highly ranking documents are combined with the query and provided to a language model that returns an answer to the question. A source for the answer is identified in at least one of the documents. The answer and the identified documents are presented to the user.

The invention relates to the technical field of power systems and automation thereof, in particular to a distribution network auxiliary decision-making method and system considering source load fluctuation relevance and a medium. The method comprises the following steps: firstly, collecting related information of a distribution network area, quantifying a synchronization and hysteresis association rule of multi-source heterogeneous data fluctuation, and constructing a composite feature vector and a standardized risk perception data set; defining a state space and an action space of a reinforcement learning algorithm based on the composite feature vector, and realizing auxiliary decision-making optimization of the distribution network; constructing a scene feature library, calculating the fluctuation relevance similarity between a new scene and a historical scene, and multiplexing a deep reinforcement learning model architecture and carrying out transfer learning; building a power grid digital twinborn simulation platform, designing evaluation indexes, generating candidate schemes, deducing the candidate schemes, selecting recommendation strategies and storing the recommendation strategies in a strategy knowledge base.

The invention relates to the technical field of digital factory production management, and discloses a digital factory-oriented multi-target production plan optimization method and system, and the method comprises the steps: decomposing an enterprise order into a plurality of subtasks through a production task decomposition module, and extracting related information; the resource dynamic evaluation module collects data in real time to generate a resource state matrix; the multi-objective optimization algorithm module constructs a model and adopts an improved non-dominated sorting genetic algorithm to solve; the dynamic priority distribution module adjusts the priorities of the sub-tasks according to the real-time data; and the conflict resolution unit is used for solving resource allocation conflicts. The method can accurately decompose tasks, evaluate resources in real time, collaboratively optimize multiple targets, flexibly deal with abnormities, efficiently resolve conflicts, comprehensively improve the production efficiency and benefits of the digital factory, and effectively solve the complex problems in the production plan making and optimizing process of the digital factory.

The invention relates to the technical field of network security, in particular to a network security analysis method and system based on big data. Comprising the following steps: collecting related multi-source heterogeneous data of a network, and carrying out standardized processing such as cleaning and de-noising; network analysis is carried out based on the preprocessed data, network traffic is analyzed in real time by using machine learning and deep learning algorithms, and abnormal conditions are detected; constructing a risk prediction model according to a network analysis result and related information, and predicting a future network security risk level; if the risk level exceeds the threshold value, determining a security event source and a responsibility subject through data tracing; and finally, generating a safety response strategy according to risk prediction and data traceability results, and performing disposal. The corresponding system covers the modules of data acquisition, preprocessing, network analysis, risk prediction, data tracing, security response and disposal and the like, and all the modules work cooperatively to form a complete network security analysis and guarantee system, so that the stable operation of the network system is guaranteed.

The embodiment of the invention provides a document generation method and device based on artificial intelligence, and the method comprises the steps: extracting multi-modal data features of a historical multi-modal file through natural language processing and a computer vision algorithm, and constructing a corresponding knowledge graph according to the multi-modal data features, converting the multi-modal data subjected to feature extraction into high-dimensional vectors by using a vectorization algorithm, and storing the high-dimensional vectors to form a vector library; splitting a current document generation task into a plurality of sub-tasks by adopting a task planning algorithm, and executing the sub-tasks at the same time to obtain a first document; performing iterative optimization of document content according to the document first draft, the cue word and the language model to obtain an optimized first draft, acquiring related information from the vector library by using an attention mechanism-based retrieval algorithm, and fusing the related information and the optimized first draft through a text generation algorithm to obtain a final document; according to the invention, the accuracy and intelligence in the document generation process can be effectively improved.

The invention relates to an AI-driven document data structured storage and retrieval method, which comprises the following steps of: analyzing and understanding document contents by utilizing a natural language processing technology, extracting structured question and answer knowledge, and constructing a structured question and answer knowledge base; a natural language processing technology and a large pre-training language model are utilized to analyze and understand a query request and a historical dialogue of a user, real intentions and demands of the user are extracted, and structured demand data are generated; and according to the user input and the demand analysis result, vectorizing the user input by using the pre-training language model, extracting related information from the vector database through a dynamic retrieval strategy, and generating and outputting a final answer. According to the method, deep analysis is performed on the document through a natural language processing technology, structured question and answer knowledge is extracted, and the performance and user experience of a question and answer system are improved by utilizing the semantic understanding ability of a large model.

The embodiment of the invention provides a city emergency command and dispatch system based on Internet of Things perception, which comprises a data acquisition module, a data processing and analysis module, an emergency resource management module, a command decision module, a communication dispatch module and a visual display module, the data acquisition module acquires and preprocesses multi-source heterogeneous data through various sensors and an intelligent terminal; the data processing and analysis module analyzes data by using technologies such as big data, predicts the trend of an emergency, identifies risks, and generates a report and an early warning; the command decision-making module generates and optimizes a command decision-making scheme according to the early warning and the pre-arranged plan; the emergency resource management module manages resources and deploys the resources according to a scheme; the communication scheduling module realizes high-speed transmission and equipment interconnection based on various communication technologies; and the visual display module is used for visually displaying related information by virtue of a GIS (Geographic Information System) and a three-dimensional modeling technology. Through cooperation of all the modules, the urban emergency processing capacity can be improved.

The invention provides a retrieval enhancement generation method and system based on a large language model. The method comprises the steps that input query information of a user is obtained; performing rewriting and key information extraction on the input query information based on a large language model to obtain a first query instruction and a second query instruction; according to the input query information, identifying a user intention based on a large language model and performing intention classification to obtain an intention classification result; according to the first query instruction and the second query instruction, performing multi-path mixed retrieval through a preset multi-source knowledge base to obtain an initial retrieval result; according to the intention classification result, performing result rearrangement and screening on the initial retrieval result to obtain an enhanced cue word; and inputting the input query information and the enhanced cue word into the large language model to obtain a retrieval enhanced generation result. According to the method, the query demand and intention of the user can be accurately recognized, related information is retrieved in an open domain in a high-precision manner, and the instantaneity, the accuracy, the specialty and the reply quality of information retrieval are improved.

The invention discloses an intelligent diagnosis method and system based on a knowledge graph and a large model, and relates to the technical field of large model application, and the method comprises the steps: constructing a medical knowledge graph; a dialogue interface is designed, and the dialogue interface utilizes a large model to guide a patient to describe symptoms and automatically analyzes and extracts chief complaint information; querying related information through the medical knowledge graph, and integrating and sequencing to form a disease condition information base; pre-training the large model, simulating doctor questions and answers based on the illness state information base, guiding the patient to describe symptoms and signs in detail, and updating the illness state information base; inquiring the medical history through a dialogue interface, and dynamically adjusting the problem; the large model comprehensively analyzes chief complaints, signs and medical history, simulates diagnosis thinking, gives preliminary diagnosis results and suggestions, and displays the results and suggestions to patients or doctors. The diagnosis accuracy and efficiency can be improved, and the problems that traditional medical diagnosis depends on doctor experience and is high in subjectivity, low in efficiency and the like are solved.

The invention relates to an alarm root cause positioning method of an operation and maintenance platform. The method comprises the following steps: acquiring and processing monitoring data; constructing a software and hardware topological knowledge graph; analyzing call chain data; merging the maps; processing the alarm data, and classifying the alarm data; finding an alarm causal relationship; predicting time sequence performance index data; constructing a monitoring operation and maintenance knowledge base; carrying out alarm convergence and root cause positioning; and performing alarm interpretation and processing opinions. According to the method, the topological graph is created and configured on the basis of the CMDB, related information such as call chains, alarm causal relationships and faults of performance index classes is added, and the physical link logic relationships between the components and the virtual machine or the host machine where the components are located are obtained through the CMDB so as to discover the mutual call relationships of application and service levels between the components. And the monitoring operation and maintenance knowledge base is used for carrying out professional interpretation on alarms and abnormal events and giving expert-level disposal suggestions. The expandability is considered in the system design, and more data sources and algorithms can be conveniently integrated in the future.

The invention relates to the technical field of artificial intelligence, and provides a retrieval joint optimization method for a retrieval enhancement generation system, which comprises the following steps: constructing a knowledge base and a vector library of a large language model, and obtaining an input problem of a user; performing keyword matching and similarity comparison on the input question and a knowledge base and a vector base of the large language model, and extracting text blocks from the knowledge base according to a result to obtain an initial retrieval candidate set; extracting related information in the initial retrieval candidate set and the large language model, and generating an initial external related information block set and an internal related information block set; performing progressive information verification on the initial external related information block set to obtain an external related information block set; the internal related information block set and the external related information block set are integrated, conflict information is removed, and a final retrieval result is generated; and sending the input question of the user and the final retrieval result to the large language model, and generating a corresponding answer by the large language model. The accuracy of large language model output can be improved.

Techniques for logical text passage generation and retrieval for retrieval-augmented generation. The techniques involve processing markup language documents to generate logical text passages and their corresponding embeddings. These embeddings are indexed for efficient retrieval. Upon receiving a user utterance, a user query is formed and transformed into an embedding to query the index. Relevant text passages are identified and used to prompt a large language model (LLM), which generates a completion. This completion is then sent as a response to the user. The process effectively bridges user queries with relevant information through advanced embedding and natural language processing techniques, enabling accurate and contextually appropriate interactions within a user-agent dialogue framework.

The invention relates to an electric power knowledge graph construction method and device based on a large language model, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring initial document data from a power scene, and filtering the initial document data to obtain target power document data; extracting initial triple information from the target power document data by adopting a pre-trained large language model; matching associated information from a preset power field information base according to the target power document data; performing data correction processing on the initial triple information according to the associated information to obtain target triple information; and establishing an electric power knowledge graph according to the target triple information. By adopting the method, the power information processing accuracy can be improved.

The invention provides an analysis method and system fusing a large model and a knowledge graph technology, and relates to the field of deep learning, and the method comprises the steps: firstly extracting the text content of an industrial technology related original file from a patent database, an academic literature library and a policy file, and constructing an industrial technology knowledge graph according to the text content; then, relevant information nodes are positioned through an industrial technology knowledge graph to extract industrial technology query matching content, significant semantic interaction analysis is carried out by utilizing a large language model, and then a question answer text matched with user consultation is generated by utilizing an intelligent answer robot based on the large language model; therefore, semantic interaction analysis and automatic answer generation are carried out on industrial technology related files and user consultation questions, more personalized and comprehensive question answering texts related to industrial technology analysis are provided for different user consultation questions, and the performance of a question answering system is improved.

The invention discloses an information scanning and penetration test path planning method in a Windows domain based on reinforcement learning. The method comprises the following steps: carrying out information detection on a target Windows domain environment, surveying and mapping a network topology of the target Windows domain environment, establishing connection with a target machine by utilizing protocols such as LDAP (Lightweight Directory Access Point) and the like, and collecting related information in the domain; the method comprises the following steps of: collecting, sorting and abstracting detected related information, solving a multi-stage sequence decision problem by utilizing a Markov decision process, realizing environment simulation, constructing a reinforcement learning agent, generating a penetration test path by performing interactive training with a simulation environment, and performing adjustment according to a reward strategy so as to obtain a penetration test result. And searching an optimal penetration test path by accumulating rewards, constructing a Windows domain penetration test model, and finally generating the optimal penetration test path. According to the method, collection of information in the Windows domain and planning of the penetration test path are realized, and finally, the environmental safety of the Windows domain is evaluated and maintained.

The invention discloses an intelligent question answering system and method for cross-domain knowledge reasoning, and relates to the technical field of intelligent question answering. In order to solve the problem that an existing intelligent question answering system is limited by technical shortages and cannot give satisfactory reply to a user in cross-domain question processing, the adopted scheme comprises the steps that a domain knowledge base construction module collects multi-domain knowledge data, and the multi-domain knowledge data is stored in a corresponding domain vector knowledge base after being preprocessed and vectorized; the user interaction module provides an interface, receives input, interacts and returns a result; the field identification module identifies the field and extracts key information by using a large language model; the knowledge retrieval module retrieves related information accordingly; the cross-domain knowledge reasoning module is used for reasoning a knowledge logic relationship of each domain and guiding a large language model to integrate fused knowledge; and the intelligent question-answering module generates prompt words, inputs the prompt words into the large language model to obtain a final response, and returns each result to the user interaction module for display. According to the method, knowledge from multiple fields can be processed, and the method is suitable for various different types of problems and scenes.

The invention discloses a virtual historical character dialogue method and system with role knowledge and context awareness, and relates to the technical field of man-machine interaction, and the method comprises the steps: constructing a multi-level role depth model; when a question of a current user is received, identifying information of a virtual scene where the current user is located, analyzing micro-expressions of the face of the user and voice rhythm characteristics of speech of the user, analyzing an emotional state and an interaction intention of the user based on a multi-modal fusion algorithm, and generating a user state vector; executing a dynamic Prompt construction program, extracting related information from the multi-level role depth model and the user state vector, and generating a structured Prompt; and inputting the structured Prompt into a large language model, generating a reply text conforming to role features based on questions of the current user, and driving a virtual character model. The method solves the problem that in the prior art, virtual historical figures cannot provide real immersion and credible interactive experience with emotional connection.

The present application provides a data processing method, a category identification method and a computer device, in which, firstly, node information is screened out based on node edge data and feature information, that is, K first nodes with rich structures and high feature discrimination are located, and then a feature similarity is calculated based on relevant information of the first nodes. On the other hand, since a calculation amount of the feature similarity of the node is relatively small, for a case that model training and prediction of node category are completed at the same time, a second node can include a node to be classified, and a model parameter used in category prediction is obtained by performing parameter iterative updating with taking the node to be classified as an unlabeled node.

The invention discloses an intelligent question answering system based on a large language model and a knowledge base, and particularly relates to the technical field of artificial intelligence application, comprising a large language model module, a knowledge base module, a retrieval and matching module, an answer generation module and a user interaction module; according to the method, on the basis of a pre-trained large language model and a structured knowledge base, key entities and semantic intentions in user questions are extracted through a multi-level text analysis technology, and preliminary answers are generated; the system combines domain knowledge in a knowledge base, uses vector retrieval and a graph database to efficiently retrieve related information, dynamically fuses retrieval results and generates answers through an attention mechanism and a gating mechanism, and ensures logic consistency and fact accuracy. The system supports multi-modal input and output, and realizes continuity of multiple rounds of dialogues through a memory network; user feedback data optimizes system performance through strategy gradient, and continuously improves answer quality and field adaptability.

A method and system for designing curing processes is disclosed. The method includes obtaining design requirements using a requirement gathering agent, determining potential ranges of recipes and operating conditions with an operations specialist agent, identifying suitable material options and assessing corresponding properties with a material specialist agent, defining dimensions and shape aspects of the design using a design specialist agent, extracting and reasoning relevant information with a knowledge processing and retrieval agent, formulating a final requirement specification with an experiment enabler agent, generating a first set of experiments based on the final requirement specifications using an experiment designer, performing, by a predictive model design agent implementing a prediction model, real-time predictions for dynamic conditions, updating, by a predictive model optimizer agent implementing a continual learning framework, the prediction model in real-time; and optimizing and updating, by a process optimizer agent, the prediction model iteratively based on feedback from experiments and simulations.

A method of controlling a broadcast receiver and which includes displaying a broadcast program on a screen of the broadcast receiver, determining if a broadcast-related information enlargement mode is selected, and enlarging the broadcast-related information on the screen of the broadcast receiver when the determining step determines the broadcast-related information enlargement mode is selected.

An intelligent legal document generation and review system and associated methods are disclosed. The system comprises one or more processors coupled to memory storing instructions to provide a user interface for receiving user input, execute a natural language processing subsystem to extract relevant information, access a legal rules database, store document templates, and execute an AI algorithm. The AI algorithm retrieves a relevant template based on user input and extracted information, populates the template to generate a customized legal document, and stores the document. An attorney feedback loop allows attorneys to provide feedback that the AI algorithm learns from to improve document generation. The AI algorithm collaborates with attorneys to revise and finalize documents based on the feedback. The system streamlines document preparation, automates complex tasks, and provides expert guidance to help users adhere to legal requirements across jurisdictions.

The present invention relates to the field of artificial intelligence technology, and in particular to a dynamic relevance enhanced retrieval generation system and method driven by an intelligent knowledge graph. The knowledge graph construction module of the present invention identifies and extracts entities and entity relationships from a text document collection with a massive amount of text documents to construct a knowledge graph and a knowledge graph index, and optimizes the index of the knowledge graph, which greatly shortens the query response time and improves the user experience. The related document collection module performs in-depth analysis and relevance evaluation on the relationship between text documents and user queries to extract related text documents, thereby ensuring the diversity and depth of the retrieval results. The retrieval enhancement generation module retrieves relevant information from the knowledge graph based on user queries and related text documents, and combines the retrieved relevant information with the user query to generate an answer, which helps to achieve more fine-grained related content retrieval, thereby improving the quality of the answer.

Systems are provided for implementing methods for generating and processing fix suggestions for alerts produced by code analysis tools. The methods involve receiving an alert, parsing the alert to identify relevant information, and assembling a prompt for a Large Language Model (LLM). The prompt includes a general description of the problem, a description of the alert message, a source-code location, and a request for a proposed fix to the alert. The prompt is sent to the LLM, and a response is obtained. The response includes a proposed fix comprising a set of edits to be applied to the source code and / or configuration files. The response is processed and validated, and a fix suggestion is assembled and provided based on the response. The fix suggestion includes a natural language explanation of the proposed fix, suggested source-code changes, and selectable options for accepting, rejecting, and editing the fix suggestion.

The invention provides a multi-agent strategic scenario generation system based on a large language model, and the system comprises the following steps: carrying out the modeling of a scene and a system, and carrying out the system modeling of an attempt to record a case, deduce a situation, an event, a scenario, a strategic-battle-tactical-level red-blue party subsystem and a white party subsystem; the method comprises the following steps: initializing a red party attempt to record cases and a blue party attempt to record cases, when a user uses the system, prompting that relevant information of military deduction needs to be input, and after the information is input according to requirements, the system uses a global attempt record generation agent to receive the information input by the user and generate an attempt record in a JSON format. According to the multi-agent strategic scenario generation system based on the large language model provided by the invention, the strategy-battle-tactical multi-level agent vertical cooperation relationship-based game subsystem is designed, and the task granularity of scenarios designed by the large language model is refined through the multi-level game subsystem; and the scenario design quality is effectively improved.

The invention discloses a new energy intelligent safety team system, and relates to the technical field of new energy, the new energy intelligent safety team system comprises a central regulation and control module, the central regulation and control module is in communication connection with a field operation management module, an educational training module, a risk pre-control module, a hidden danger checking and emergency management module and an intelligent hardware integration module, and the field operation management module is used for providing operation guidance for team personnel through the intelligent terminal, pushing safety risk information in an operation environment in real time, and performing task allocation, progress tracking and completion condition feedback. According to the invention, by monitoring key information such as the working state of team personnel, the equipment operation condition and the environmental parameters in real time, abnormal or potential risks are found in time, and related information is automatically pushed to management personnel, so that the safety management capability of the team is enhanced, safety accidents are effectively prevented, and the safety of personnel and property is guaranteed.

The embodiment of the invention relates to a reply text generation method and device, computer equipment and a storage medium. After an input text is preprocessed, a target text is obtained; acquiring context information corresponding to the target text, a first prompt word template and a first keyword; retrieving related information corresponding to the input text from a first database according to the input text, the context information, the first cue word template and the first keyword to obtain a retrieval result; generating cue words of a large language model according to the input text, the context information, the first cue word template, the first keyword and the retrieval result; and inputting the cue word into the large language model to output the reply text through the large language model. Therefore, after the input text is combined with the context information, the cue word template of the industry and the keyword to retrieve the related information, the cue word of the large language model is generated according to the retrieval information, the reply text is accurately generated through the large language model, and the question and answer accuracy and the user satisfaction degree are improved.

The invention discloses a construction method, system and equipment of a power dispatching knowledge question-answering system and a storage medium. The construction method comprises the steps of obtaining a power dispatching semantic document needing to be processed by the power dispatching knowledge question-answering system; sequentially carrying out character-based segmentation, proposition conversion and proposition combination on the power dispatching semantic document on the basis of the large language model and the related cue words to obtain a plurality of text blocks; based on the large language model and the related prompt words, identifying and extracting entities related to power dispatching and relationships among the entities from each text block; constructing a local graph for each text block on the basis of the large language model and the related prompt words, the entities extracted from each text block and the relationship among the entities; traversing each text block, and combining all the local graphs into a global graph; and on the basis of the large language model and the related prompt words, according to the question type queried by the user, a reply text is correspondingly generated by matching a minimum local graph which is most related to the global graph in the global graph.

The invention relates to the technical field of sea area development, and particularly discloses a sea area development suitability evaluation method and system, and the method employs a natural language processing technology based on deep learning to carry out the data processing of a sea area development suitability evaluation document. A man-made judgment adaptability grading label and evaluation index related information of sea area development are extracted, semantic coding and semantic feature enhancement processing are carried out on the evaluation index related information, intelligent evaluation of sea area development suitability is achieved, and then an intelligent evaluation result and the man-made judgment adaptability grading label are compared and analyzed. Therefore, the reliability of manual judgment is verified. Through the mode, the subjectivity deviation in the sea area development suitability evaluation process can be effectively reduced, the evaluation objectivity and accuracy are improved, and therefore a more reliable basis is provided for subsequent sea area development activity decision making.

The invention relates to a method, a system and equipment for generating a large model SQL (Structured Query Language) based on business domain semantic enhancement and multi-round voting. The method comprises the following steps: acquiring a natural language input by a user to recognize and judge a business field related to user query; performing semantic annotation and expansion on the input query; organizing related information into Prompt, inputting the Prompt into a large language model, and generating an SQL statement; generating a plurality of candidate SQL statements, and selecting the candidate SQL statements with the highest occurrence frequency as output; and submitting the finally output SQL statement to an actual database system for execution, and returning and displaying a query result. Through the technologies of business domain division, data structure semantic annotation, multi-round candidate generation, voting screening and the like, SQL generation accuracy and system robustness of natural language query are remarkably improved, query intentions and field constraints in business scenes of enterprises such as banks and the like can be accurately recognized, field matching errors are avoided, and the query efficiency is improved. And through multi-round iterative generation and consistent voting screening, the correctness and stability of the output SQL statement are ensured.