141 results about "Knowledge acquisition" patented technology

The invention discloses a multi-agent dynamic arrangement method based on multi-modal analysis and adaptive retrieval, and relates to the technical field of artificial intelligence and information retrieval. Comprising the steps of S1, converting a text, an image, structured data and voice content input by a user into a unified multi-mode semantic representation, S2, converting the unified multi-mode semantic representation into a specific execution process, and S3, automatically scheduling a reasoning agent, a knowledge obtaining agent and an execution agent according to DAG nodes, task elements and available resources, and obtaining the task elements and the execution agent according to the reasoning agent, the knowledge obtaining agent and the execution agent. S4, after task process construction and agent arrangement are completed, dynamic retrieval, evidence convergence and strategy optimization are carried out on information requirements related to a user task, so that a reasoning agent obtains complete knowledge support with consistent context, and S5, knowledge evidence is combined with a task process, so that the task process is completed. The method comprises the following steps: step S6, implementing problem solving, strategy generation and task closed-loop execution through a reasoning agent, step S6, performing actual operation on a target task by an execution agent according to an executable instruction sequence output by the reasoning agent, and outputting a result, and step S7, performing result verification according to an output result returned by the execution agent, and the correctness, integrity and consistency of an output result are examined through rule verification, model evaluation and evidence alignment.

The invention relates to the technical field of natural language processing, and discloses a knowledge base question and answer platform construction method based on a large language model, which comprises a knowledge acquisition module, a data preprocessing module, a text processing module, a vectorization module, a question understanding module, a mixed retrieval module, a prompt generation module, an answer generation module and an answer quality analysis module. A secondary inquiry processing module and a feedback learning module; according to the method, a semantic segmentation algorithm is combined with semantic retrieval and keyword retrieval, so that the flexibility is high; normalized prompts are constructed, input is performed according to correlation sorting, and the accuracy of answers is improved; multi-dimensional confidence evaluation is introduced, strict multi-layer security and compliance filtering is set, and the reliability of the system is ensured; the relevance of multiple rounds of dialogues is judged and complemented, so that interaction is more natural and efficient; knowledge is collected and updated in real time, a knowledge base and a retrieval strategy are continuously optimized, and a closed loop of data-application-feedback-tracing-optimization is formed.

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 electric power big data automatic reasoning platform and an electric power distribution system, and relates to the technical field of electric power systems, and the platform comprises a knowledge acquisition unit which collects and preprocesses electric power internal and external data, and converts the data into structured data through a knowledge processing unit; organizing the triple data by the dynamic knowledge graph construction unit to form an initial graph; the updating unit monitors a new dynamic state in real time and corrects or adds atlas content; the reasoning unit is based on the dynamic graph, power fault accurate reasoning and future demand trend prediction are achieved through a fault diagnosis and demand prediction algorithm, efficient integration and dynamic evolution of power knowledge are achieved through construction and real-time updating of the dynamic knowledge graph, timeliness and accuracy of the graph are ensured, and reliable data are provided for fault diagnosis; through a closed-loop architecture of data acquisition-inference analysis-scheme making-execution control, an intelligent sensor and an optimization algorithm are combined to generate a distribution scheme adaptive to a scene, and the power distribution adaptability and economy are improved.

The invention relates to the technical field of term libraries in the field of constructional engineering, and discloses a construction application method and system for a term library in the field of constructional engineering, and the method comprises the steps: preprocessing unstructured data to obtain structured constructional engineering text data, and extracting the structured constructional engineering text data based on a joint extraction architecture to obtain an extraction result; the method comprises the steps of obtaining structured data of terms and building engineering triple information, establishing a standard library and a term library according to the structured data, constructing a term-standard double-layer knowledge graph based on internal association of the standard library and the term library and the building engineering triple information, and responding to query of a user. And calling the standard library, the term library and the term-standard double-layer knowledge graph by a mixed decision-making mechanism based on rule reasoning and graph neural network learning to obtain a query result. According to the invention, the full-life-cycle intelligent closed loop of construction engineering terms from extraction, management to application is realized, and the problems of difficult acquisition of industry term knowledge, complex management and low application efficiency are solved.

The invention relates to an AD-RAG-based vehicle after-sales maintenance document analysis and maintenance knowledge acquisition system and method, and the system comprises a document analysis module which carries out the layout analysis and document recognition of after-sales maintenance document information, and obtains structural data; the knowledge organization module is used for establishing an association relationship between the text data and the structural relationship in the structured data to obtain a maintenance knowledge graph; the knowledge retrieval enhancement module is used for analyzing and expanding the vehicle fault query request based on an AD-RAG model to obtain an expanded query request, and querying in a maintenance knowledge graph based on the expanded query request to obtain document fragment information; and the task decomposition and reasoning optimization module analyzes and decomposes the extended query request to obtain at least one fault sub-problem sequence, and performs fault reasoning through a preset fault reasoning model based on the fault sub-problem sequence and the document fragment information to obtain a fault maintenance suggestion result. The retrieval requirement can be better met, and the obtaining efficiency of the maintenance knowledge can be improved.

The invention discloses a multi-agent collaborative knowledge reasoning system based on a large language model, and relates to the technical field of intelligent manufacturing and artificial intelligence. Natural language output of a large language model is converted into rules, facts and ontology fragments which can be directly consumed by an inference engine through knowledge obtaining and compiling, continuous increment updating of cross-domain knowledge is achieved in cooperation with metadata with sources and timestamps, and the limitation that a traditional static knowledge base is difficult to cover dynamic faults is overcome; secondly, a blackboard and agenda mechanism is used as a cooperative carrier, intermediate assertions of intelligent agents such as vibration, circuits and logs are published and subscribed in a structured mode, and a conflict resolution and consistency verification module carries out unified judgment according to specificity, time freshness and source credibility; therefore, delay and uncertain accumulation caused by long-chain natural language dialogues are avoided in a strong real-time scene.

The invention relates to the technical field of computers, and discloses a fragmentation block chain federal learning method based on a large language model multi-agent, and the method comprises the steps: S1, initializing a client; s2, dynamic fragmentation scheduling and distribution; s3, generating and uploading local knowledge; s4, intelligent agent collaborative routing and knowledge acquisition; s5, knowledge fusion and model updating; and S6, repeatedly executing the steps S3 to S5 until the model converges or reaches a preset number of iterations. According to the invention, under a decentralized and fragmented federated learning architecture, the complex reasoning ability of a large language model and the autonomous cooperation mechanism of three multi-agent systems, namely a fragmented scheduling agent, a fragmented knowledge state agent and a global knowledge routing agent, are deeply fused; according to the mechanism, dynamic optimization of a bottom layer fragment structure and intelligent routing of high-value knowledge are achieved in an intelligent mode, and therefore the overall efficiency and model performance of a system under the condition of heterogeneous data and heterogeneous equipment are remarkably improved.

The invention discloses an intelligent auxiliary decision-making method and system for multi-modal data fusion of multiple myeloma, and relates to the technical field of medical information, and the method comprises the steps: obtaining multi-source clinical data and authoritative literature of a patient, and building a literature database after preprocessing; configuring an interface to automatically capture new literatures, and generating a dynamic knowledge base in combination with semantic conflict detection, knowledge extraction and expert auditing; according to the knowledge base, fusing the multi-modal clinical data by adopting federal learning to generate a fusion feature matrix; constructing a causal relationship network, combining matrix prediction and generating a causal evidence network, and grading the causal relationship; and associating the knowledge base with the evidence network, generating an interpretable report containing a prediction result and the like, and realizing full-process traceability. Through three designs such as automatic knowledge acquisition and updating, the static lag problem of the knowledge base is broken through, and the medical frontier is synchronized; a causal reasoning system is constructed, defects of a traditional model are overcome, transparent reasoning is achieved, and the credibility of doctors is improved.

The invention relates to the technical field of knowledge graph construction, in particular to a knowledge graph construction and enhanced generation method and equipment for health and care, and a medium, which can solve the problem of suitability optimization of a large model in the field of health and care through reinforcement learning and semantic information technologies, and provide large model application services with professional adaptation and high interpretability. For knowledge graph construction, the extraction precision and the fine adjustment efficiency of a base large model for knowledge in the health and care field are improved through reinforcement learning, semantic association is reinforced by means of evidence chain fusion to improve graph information density, and accurate classification and summarization of knowledge are achieved based on multilevel clustering; aiming at enhanced generation, retrieval pertinence is improved through field adaptability optimization of a problem analysis model, comprehensiveness and accuracy of knowledge acquisition are guaranteed through multi-path recall and reordering, and the problem of interpretability of large model generation content is solved through traceability connection.

The invention relates to an electric power intelligent knowledge retrieval method and device based on an RAG model, computer equipment, a computer readable storage medium and a computer program product, and can be applied to the technical field of computers. The method comprises the steps of obtaining a query request; performing semantic analysis processing on the query request to obtain a query semantic feature of the query request; according to the query semantic features, candidate knowledge content is retrieved from a pre-constructed electric power knowledge base; screening the candidate knowledge content to obtain a target retrieval result of the query request; inputting the target retrieval result into a pre-trained power field content answer model for content answer processing to obtain preliminary answer content of the query request; and performing security filtering processing on the preliminary answer content to obtain a target answer result of the query request. By adopting the method, the power knowledge acquisition efficiency can be improved.

According to the electric power data prediction method based on large language model auxiliary knowledge graph construction provided by the invention, a high-coverage electric power knowledge graph is automatically constructed through a large language model, so that the problems of low knowledge acquisition efficiency and insufficient semantic relationship recognition accuracy of a traditional method are solved; through a multi-path causal attribution mechanism, a multi-hop and multi-relation path in the knowledge graph is effectively converted into a prior adjacency matrix which can be utilized by a neural network, and structured fusion of domain knowledge is realized; through the synergistic effect of the time sparse attention and the mixed adjacency matrix, the modeling precision of the power data space-time dependency relationship is remarkably improved, and an important technical support is provided for precise scheduling and optimized operation of a smart power grid.

The invention relates to the technical field of data retrieval, in particular to a FastGPT-based intelligent question-answering system for construction project quality inspection and detection standards. According to the technical scheme, the method comprises the steps of external knowledge acquisition, document processing, vectorization, vector database, retrieval and context generation and intelligent question and answer, data can be collected by a system, a semantic segmentation technology, a QA pair generation technology and a high-dimensional vectorization technology are utilized, in combination with M3E and OpenAIEmbedding models, Top-K similarity retrieval and context dynamic recombination are achieved, and structured and hierarchical professional answers are generated. According to the method, the intelligent management and real-time application capability of the construction project quality inspection and detection standard can be remarkably improved, the manual retrieval and interpretation cost is reduced, and the digital and intelligent requirements of an engineering project are met.

The invention discloses an intelligent fault diagnosis method and system for welding equipment. The method comprises the steps that a large language model analyzes according to input fault description to obtain a core retrieval dimension; based on a pre-constructed welding equipment fault knowledge graph, performing primary screening and link completion on the core retrieval dimension to obtain one or more fault link strengths and case success rates; according to the fault link strength and the case success rate, diagnosing the credibility of the link, and comparing the credibility of each link to obtain an optimal diagnosis result; wherein when a new fault case is added to the welding equipment fault knowledge graph, the new fault case is automatically updated through a large language model; according to the method, the problems of knowledge acquisition and semantic understanding are solved through the large language model, the problems of knowledge storage and link tracing are solved through the knowledge graph, full-process automatic diagnosis from fuzzy input to landing reporting is achieved, the technical pain point of a traditional scheme is solved, and the practical requirement of an industrial welding scene is met.

The invention discloses an intelligent question and answer method and system for a large model ship field based on retrieval enhancement generation, and the system comprises a fine tuning data integration module, a model fine tuning module, a model reasoning module and a module integrating various technologies, and aims at achieving the efficient management, intelligent retrieval and precise question and answer of complex documents in the field. According to the system, through organic cooperation of three core modules of document preprocessing, high-precision retrieval and large-model fine-tuning reasoning, the system adopts multiple index structures, and rapid positioning and semantic matching of documents are achieved. Through a large model fine tuning technology, the system adapts a general pre-training model to a ship domain task and endows the ship domain task with a domain specifying ability, and the system can quickly respond to multiple rounds of question and answer requirements of a user and dynamically adjust generated answers to meet the requirements of different contexts. According to the method, the threshold of knowledge acquisition and utilization is reduced for the ship industry, resource optimization configuration and technical progress are promoted, and a wider space is created for future development of the industry.

The invention discloses an electromagnetic interference risk assessment method based on expert knowledge and a neural network, and the method comprises the steps: building an electromagnetic interference risk assessment index system of a to-be-assessed object, bottom layer indexes of the index system comprise a power grid ripple coefficient, power grid peak signal conduction emission, power grid harmonic characteristics, electromagnetic emission characteristics, electromagnetic sensitivity characteristics, filtering characteristics and conduction and radiation safety margin. Establishing a potential interference source and potential sensitive equipment electromagnetic compatibility evaluation data set by using an expert knowledge method; and using the neural network to carry out electromagnetic interference risk assessment training and assessment of the to-be-assessed object. The method can give full play to the advantages of strong pertinence and high flexibility of expert knowledge and the advantages of strong ability of automatic knowledge acquisition and nonlinear mapping of a neural network, and realizes adaptive assessment of electromagnetic interference risks according to real-time acquisition and analysis of an electromagnetic environment; according to the method, manual parameter setting is not needed any more, the evaluation process is easier to implement, and the reliability of the evaluation result is higher.

The invention belongs to the technical field of computer network security, and discloses a power network security knowledge ontology modeling method, which comprises the following steps of: firstly, collecting multi-mode heterogeneous data such as power monitoring, security equipment and threat intelligence in parallel; then, adopting a hybrid strategy, on one hand, constructing a top-layer seed ontology based on a domain standard, and on the other hand, automatically extracting an entity relationship from the text by utilizing a deep learning model; secondly, associating multi-source knowledge and solving conflicts through entity alignment and sequential logic fusion, and generating a consistent and credible global knowledge view; and finally, establishing an ontology self-evolution mechanism based on reinforcement learning, dynamically adjusting knowledge weight and automatically expanding a mode, realizing deep understanding, accurate prediction and self-adaptive evolution of network threats, and improving the active defense level of a power system. According to the method, the core problems of one-sided knowledge acquisition, poor fusion capability, static model evolution incapability and the like in the prior art are solved.

The invention relates to the field of intelligent manufacturing and digital process planning, in particular to a knowledge-driven automatic generation method for a part machining process and a related product, and the method comprises the steps: constructing a machining-process-oriented knowledge graph, and coupling the knowledge graph with a large knowledge model to form a feedback closed loop; extracting process knowledge units from the multi-source data, and performing quantitative scoring and credibility screening on the process knowledge units based on a preset knowledge evaluation algorithm to obtain a high-reliability process knowledge data set; performing fine-grained attribute relation extraction on the process knowledge in the process knowledge data set, structuring an extraction result, and dynamically updating the extraction result to the knowledge graph to realize incremental updating of the knowledge; through collaborative innovation of four core links of efficient and automatic knowledge acquisition, structured and refined process knowledge expression and dynamic extension and real-time updating capability generation, the technical bottleneck in traditional process planning is solved.

The invention discloses an automatic garbage classification method and system based on machine learning, and relates to the technical field of environmental protection, and the method comprises the steps: carrying out the multi-physical field dynamic excitation and response data collection of garbage articles, obtaining multi-modal feature data, and carrying out the environment disturbance correction of the multi-modal feature data; inputting the corrected multi-modal feature data into a feature decoupling network constrained by a physical mechanism, and decoupling and outputting essential attribute feature vectors and representation attribute feature vectors; inputting the essential attribute feature vector into a classification decision unit, and outputting a classification result, a confidence score and an uncertain sample mark based on a multi-level classification decision of essential attributes; and for the samples indicated by the uncertain sample marks, starting a physical verification-oriented active knowledge acquisition mechanism, acquiring classification labels and updating a feature database. According to the invention, the accuracy and adaptive evolution capability of garbage classification in a complex real scene are improved.

The application discloses a kind of sequence model and knowledge graph combined question and answer method, comprising: knowledge acquisition processing method, knowledge graph construction method, model construction method, question determination and answer generation method.Corresponding question and answer strategy is designed for different types of data sets, "field professional knowledge semantic data" is constructed from field professional knowledge data set, and professional answer in knowledge graph is obtained by keyword extraction and template matching."Field knowledge basic question and answer semantic data" is constructed from field knowledge basic question and answer data set, and the best answer of field knowledge chat data set is obtained using sentence vector similarity algorithm, to train Seq2seq model, as the supplement of knowledge graph.Combining the above question and answer strategy, this method can not only answer professional field knowledge, but also answer daily chat system.The method can accurately and efficiently answer questions in different fields, to some extent, so that the question and answer system can understand the intention of user, and is more intelligent.

The invention provides a knowledge base retrieval method and device based on a page type storage architecture, and relates to the technical field of artificial intelligence, and the method comprises the following steps: receiving a knowledge retrieval request sent by a current large model; matching a semantic vector corresponding to the knowledge retrieval request with a semantic vector of each knowledge block in a page table, and determining memory block numbers and page numbers of a plurality of target knowledge blocks; reading each target knowledge block in the memory based on the memory block number of each target knowledge block, and combining each target knowledge block based on the page number of each target knowledge block to generate a knowledge retrieval result corresponding to the knowledge retrieval request; and sending a knowledge retrieval result to the current large model. According to the method and the device provided by the invention, through an innovative index construction mode and a retrieval mechanism, in combination with a page type storage architecture and a vector distance retrieval technology, the knowledge acquisition efficiency of a large model is improved, efficient processing, rapid retrieval and flexible updating of knowledge data are realized, and the overall performance of a knowledge base is improved.

The embodiment of the invention provides a multi-modal retrieval method and device. The method comprises the following steps: for at least part of knowledge in a knowledge base, obtaining visual features and text features of each piece of knowledge; a first embedded representation and a second embedded representation of the question are obtained, the first embedded representation and the visual features belong to the same embedded space, and the second embedded representation and the text features belong to the same embedded space; obtaining a first candidate set based on the first similarity between the first embedded representation and the visual features of different knowledge; obtaining a second candidate set based on a second similarity between the second embedded representation and the text features of different knowledge; and selecting at least one piece of target knowledge from the multiple pieces of candidate knowledge based on the correlation between the question and different pieces of candidate knowledge in the multiple pieces of candidate knowledge to obtain a retrieval result.

The invention belongs to the technical field of artificial intelligence, and discloses a knowledge service management method and device fusing generative AI and enhanced retrieval. Comprising the steps of constructing a knowledge base for multi-source heterogeneous data fusion, deploying a dynamic task planning engine, executing a whole-process service, establishing an evaluation and feedback closed loop and the like. Wherein the whole-process service covers AI knowledge questions and answers, AI enhanced retrieval, AI intelligent research and reading, AI auxiliary creation and intelligent agent service, and through intention recognition, mixed retrieval, RAG enhancement, cue word engineering, Deep Research and other technologies, the whole-process run-through from accurate knowledge acquisition and deep content understanding to generative creation is realized. The problems that in the prior art, knowledge obtaining efficiency is low, literature processing intellectualization is insufficient, and scientific research processes are split are solved, a credible, controllable, processized and intellectualized closed-loop knowledge service system is constructed, the efficiency and innovation ability of scientific research work are remarkably improved, and the system is suitable for various academic research and scientific research management scenes.

1. The name of the design product: artificial intelligence voice interaction graphical user interface of electronic equipment. 2. The use of the design product: an electronic device. 3. The design points of the design product: in the graphical user interface. 4. The picture or photo that best indicates the design points: design 1 front view. 5. Design 1 is designated as the basic design. 6. The use of the graphical user interface: to improve customer information interaction experience, meet the needs of information query and knowledge acquisition, etc. 7. The change state of the graphical user interface is as follows: design 1: swipe left, design 1 front view jumps to design 1 change state figure 1. By voice waking up the virtual person or long pressing the screen, design 1 change state figure 1 jumps to design 1 change state figure 2. According to the input voice instruction, design 1 change state figure 2 jumps to design 1 change state figure 3. Design 2: by voice waking up the virtual person or long pressing the screen, design 2 front view jumps to design 2 change state figure 1. According to the input voice instruction, design 2 change state figure 1 jumps to design 2 change state figure 2. Design 3: by voice waking up the virtual person or long pressing the screen, design 3 front view jumps to design 3 change state figure 1. According to the input voice instruction, design 3 change state figure 1 jumps to design 3 change state figure 2. Design 4: by voice waking up the virtual person or long pressing the screen, design 4 front view jumps to design 4 change state figure 1. According to the input voice instruction, design 4 change state figure 1 jumps to design 4 change state figure 2. Design 5: swipe left, design 5 front view jumps to design 5 change state figure. 8. Other circumstances that need to be explained: "X" or "-" words, letters, numbers or symbols in the interface.

A blockchain-based knowledge-sharing intelligent customer service AI response accuracy optimization system, belonging to the fields of blockchain and artificial intelligence technology, is disclosed. The system includes a multi-source knowledge acquisition unit, a blockchain knowledge sharing unit, a knowledge quality assessment unit, an AI response optimization unit, and an interactive feedback and iteration unit. The multi-source knowledge acquisition unit collects customer service knowledge data from different departments, business lines, and application scenarios. The blockchain knowledge sharing unit receives pre-processed knowledge data and constructs a decentralized knowledge-sharing network based on distributed ledger technology. The knowledge quality assessment unit performs multi-dimensional quality assessments of the knowledge stored in the blockchain. The AI ​​response optimization unit trains and optimizes the intelligent customer service AI model based on high-quality knowledge samples. The interactive feedback and iteration unit collects user feedback from the intelligent customer service system. All units operate collaboratively to form a closed-loop mechanism.

The invention relates to an urban forest resource monitoring system and method based on multi-source remote sensing fusion, and the system constructs a sound-vibration cooperative control and edge intelligent processing dual-core system architecture, collects the remote sensing data of an urban complex operation environment in a high-quality manner, achieves the total-factor centimeter-level perception and robust obstacle avoidance of the urban forest complex environment, and achieves the real-time monitoring of the urban forest complex environment. And the operation safety and the data integrity are ensured. On the basis of interpretable AI and multi-modal fusion knowledge acquisition, scale pushing from a single tree to a forest stand is implemented, high-precision intelligent analysis of forest stand scale parameters is completed, and automatic and quantitative inversion of forest stand scale key parameters is realized at an airborne edge end. According to the system, key stand structure factors such as stand density, canopy density, average height and variation coefficient are automatically calculated by aggregating individual tree detection results, single-machine intelligence and group cooperation are realized, and large-scale and high-efficiency urban forest resource checking and dynamic monitoring can be realized.

The invention relates to the technical field of agent collaboration systems, in particular to a power station equipment anomaly detection decision management method based on Agent collaboration and related equipment, the system constructs four functional modules of a detection Agent, a diagnosis Agent, a knowledge Agent and a scheduling Agent, and real-time collection and standardized processing of multi-source heterogeneous detection data are achieved. The detection Agent monitors the standardized data in real time, and triggers the scheduling Agent to generate a diagnosis task tree when the standardized data is abnormal; and the scheduling Agent issues the subtasks to the diagnosis Agent for root cause analysis, or calls the knowledge Agent to obtain auxiliary diagnosis knowledge. The diagnosis Agent generates a preliminary conclusion, the knowledge Agent provides domain knowledge support, and the scheduling Agent fuses the information of the diagnosis Agent and the knowledge Agent to form a final decision containing an abnormal level, a risk level and an operation and maintenance strategy. According to the system, through data sharing and task collaboration between Agents, accurate identification, rapid diagnosis and scientific decision making of power station anomalies are realized, and the operation and maintenance efficiency and safety are improved.

The objective is to obtain a parameter adjustment content calculation device (10) capable of improving the accuracy of improving the communication quality of communications subject to quality control. The parameter adjustment content calculation device (10) comprises: an information acquisition unit (11) that acquires parameters set in one or more communication systems in which multiple communications take place, and quality information of communications subject to quality control; a design information knowledge acquisition unit (12) that acquires design information and knowledge used in the calculation of parameter adjustment content; an information storage unit (13) that stores the parameters and quality information acquired by the information acquisition unit (11) as information and stores the design information and knowledge acquired by the design information knowledge acquisition unit (12) as information; a parameter adjustment content calculation unit (14) that calculates parameter adjustment content based on the information stored in the information storage unit (13); and a parameter adjustment content output unit (15) that outputs parameter adjustment content to the communication system in which the parameters are adjusted according to the parameter adjustment content.

The invention discloses an operation state regulation and optimization method for a power distribution network containing a distributed power supply and a flexible load, and the method comprises the following steps: obtaining a topological structure and operation parameters of the power distribution network, and constructing a power distribution network operation state regulation model according to the topological structure and the operation parameters; on the basis of a power distribution network operation state regulation and control model, a traditional knowledge acquisition sharing algorithm is improved, and a spiral updating strategy is introduced to guide a search individual to approach a current candidate optimal solution along a spiral trajectory; and performing iterative solution on the operation state regulation and control model by using an improved knowledge acquisition sharing algorithm to obtain operation optimization configuration of the power distribution network. According to the method, the global search capability and the local convergence precision of the algorithm are remarkably improved, so that the operation optimization configuration can be quickly and accurately obtained, and the stability, the adaptability and the overall operation performance of the power distribution network when the power distribution network deals with renewable energy output fluctuation and load change are enhanced.

The invention discloses a large language model artificial intelligence system which comprises a modeling processing unit of a large language model, and the modeling processing unit comprises an information extractor agent, a solver agent and a checker agent; the advantage value of each information extraction mode can be calculated through a composite reward function; through the composite reward function, consideration of format verification, constraint check, semantic analysis and text similarity can be realized for each information extraction mode; analyzing the description of the natural language problem based on the composite reward function, and obtaining a candidate solution by using the generated algebraic modeling language code; and finally, verifying the feasibility and format of the candidate solution obtained by the solver, and obtaining a problem solving result. According to the method, the large language model artificial intelligence system has strong expandability and generalization ability; and the modular design is easy to understand and improve, and effective knowledge acquisition and utilization can be realized.