153 results about "Knowledge building" patented technology

The invention relates to an intelligent operation and maintenance question-answering system for cable manufacturing equipment, and belongs to the technical field of computer systems based on specific calculation models. The system comprises an edge data acquisition module, a predictive map construction module, a semantic perception module, a question-oriented reasoning module and a question and answer generation module. According to the system, multi-dimensional real-time data in the operation process of equipment is collected and structurally processed, a process knowledge graph is constructed in combination with industry knowledge, and the causal relationship and reasoning parameters in the graph are dynamically updated according to the data trend. A semantic perception module is used for recognizing the problem intention of a user, a semantic weight vector is formed to guide the reasoning process, and a problem-oriented reasoning module is made to execute joint reasoning on the basis of combining real-time data and a knowledge graph and generate an explanatory conclusion. Finally, operation and maintenance suggestions with high readability are output through a question and answer generation module, and the targets of equipment fault intelligent diagnosis, process optimization and man-machine efficient interaction are achieved.

The invention discloses a knowledge construction method and system based on a large model and an RAG technology, and belongs to the technical field of large models.According to the knowledge construction method and system based on the large model and the RAG technology, through cross-text-block mutual information calculation and RAG enhanced reasoning, the system can quantify statistical correlation between entities, and in combination with context information of an external knowledge base, potential incidence relations of cross-paragraphs or documents are mined, so that the knowledge construction efficiency is improved. A dynamic semantic segmentation strategy is adopted to ensure that semantics in text blocks are consistent, context continuity is maintained by retaining overlapped parts, multiple expressions of the same entity are comprehensively judged through a multi-dimensional anaphora resolution mechanism, the error resolution rate is reduced, dynamic segmentation and mixed retrieval are combined, and the problem of large model input length limitation is solved. And through semantic retrieval and keyword matching complementation, the recall rate is improved, and the key problems of semantic fracture, cross-text association missing, low entity alignment precision and the like in traditional knowledge construction are remarkably solved.

The invention provides a multi-agent cooperative processing system and method for multi-scene legal complaint consultation, and relates to the technical field of artificial intelligence, and the method comprises the steps: receiving a legal or complaint consultation text inputted by a user, and generating structured consultation request data; automatically generating an evidence obtaining template, and forming a standardized evidence obtaining data packet; constructing a demonstration tree and outputting a multi-scheme decision matrix; performing multi-objective optimization by combining the success rate, the timeliness, the cost and the regional qualification index, and outputting a comprehensive recommendation result; generating a knowledge unit set, and updating a regulation index and agent prompt template library; predicting a re-complaint risk and generating a remedy and optimization suggestion; and outputting review result data, and reversely updating the review result data to the agent configuration strategy in the step of the knowledge construction module. According to the method and the device, the technical targets of multi-agent cooperative processing and dynamic optimization management in the whole legal complaint consultation process can be realized, and the technical effects of improving consultation processing efficiency, enhancing scheme recommendation accuracy, reducing manual participation cost and ensuring data compliance and risk controllability are achieved.

The invention discloses an equipment diagnosis and maintenance method and system based on a large language model, a terminal and a storage medium. The method comprises the steps that multi-source heterogeneous data of target equipment is collected and preprocessed; constructing and continuously updating a historical case vector database containing equipment knowledge; state data of target equipment are monitored in real time, after fault diagnosis is triggered, the most relevant knowledge fragment is retrieved from the historical case vector database according to real-time abnormal data, and a diagnosis context is constructed; inputting the diagnosis context into a large language model for reasoning, and outputting a fault diagnosis report and a maintenance scheme; the fault diagnosis report and the maintenance scheme are presented to a user, and user feedback is collected to optimize the system. According to the method, real-time data, historical records and structured knowledge of equipment can be automatically integrated, a dynamic knowledge base is constructed, accurate and efficient diagnosis of equipment faults is realized by utilizing the powerful reasoning capability of a large language model, an executable maintenance scheme is automatically generated, and the maintenance efficiency is improved.

The invention discloses a knowledge graph generation method based on multi-source data integration, and relates to the technical field of knowledge graph generation. The method comprises the following steps: collecting multi-format data, and performing cleaning, standardization and desensitization preprocessing to ensure that the data is integrated; using the fusion model to extract entities and relationships, and adapting to multi-source data types; similarity is calculated in combination with multi-dimensional features, and entity alignment disambiguation is achieved; carrying out weighted fusion on multi-source knowledge to construct a triple, and processing relation conflicts; evaluating the quality of the atlas through multiple indexes; triggering conditions are set, incremental updating and version management are adopted, and dynamic iteration of the atlas is guaranteed. According to the method, the multi-source data preprocessing quality is improved, the entity recognition and alignment precision is enhanced, relation conflicts are solved, and a high-quality time sequence knowledge graph is constructed; incremental updating is efficient and energy-saving, version management is traceable, and multi-field dynamic application requirements are met.

The invention relates to the technical field of fault diagnosis, and provides a graph network and knowledge driven interpretable fault diagnosis method and system, and the method comprises the following steps: extracting intra-class and inter-class features for obtained operation data, and constructing a data driving graph; constructing a knowledge graph based on prior knowledge, constructing a knowledge-driven graph, and fusing the data-driven graph and the knowledge-driven graph into a unified graph structure; constructing a plurality of graph attention network sub-models, and identifying and fusing the obtained unified graph structures to obtain a diagnosis result; and performing interpretability analysis on the diagnosis result based on an input feature gradient method and a graph neural network interpreter to obtain a comprehensive diagnosis result. According to the method, more accurate, more stable and more explainable fault diagnosis and decision support is provided through data driving, knowledge driving, intra-class and inter-class feature joint extraction, multi-model fusion and fusion of an explainable analysis method.

The invention discloses a multi-priori knowledge fused cerebral apoplexy rehabilitation map convolutional network evaluation method, and belongs to the technical field of cerebral apoplexy rehabilitation evaluation. Firstly, a high-precision prior information matrix is automatically generated through a collaborative and causal relationship automatic reasoning method based on Riemannian manifold geometry and transfer entropy, the problem that in the prior art, engineering depends on artificial features is effectively solved, and interpretable physical prior guidance is provided for a model. Then, through a multi-relation graph construction and attention weighting multi-modal adaptive fusion method, spatio-temporal features and priori knowledge are adaptively fused, an optimized graph structure is constructed, and the representation ability and interpretability of the model to complex joint interaction are improved. And finally, through a space-time diagram convolutional network guided by prior information and a comparative learning collaborative optimization method, the generalization ability and evaluation precision of the model in a small sample scene are remarkably improved through data enhancement and loss function optimization.

The invention discloses an intelligent optimization system for enterprise resource planning, and relates to the technical field of enterprise resource management, and the system comprises a data collection and preprocessing layer, a knowledge construction and reasoning layer, a risk early warning and decision support layer, and a resource scheduling and execution layer. According to the invention, a knowledge graph covering various resources of an enterprise and association relationships thereof is constructed by using preprocessed data through a knowledge construction and reasoning layer, a causal relationship network among the data is established, and meanwhile, an intervention effect evaluation unit combines an anti-factual reasoning result of a causal reasoning unit to evaluate the intervention effect of the enterprise. Quantitative evaluation is carried out on different resource pre-allocation intervention schemes, and a detailed evaluation report is output, so that an enterprise can perceive and take corresponding measures in advance before a risk occurs, and can select an optimal scheme according to a scientific evaluation result when a resource planning decision is made, thereby effectively ensuring stable operation of enterprise resources, and improving the resource planning efficiency. And the operation risk caused by the resource problem is reduced.

The present invention belongs to the technical field of power natural language data question answering, and specifically relates to a method for enhancing NL2SQL questions driven by multi-source knowledge links. The method includes: constructing a power data schema using database table information and sorting out power domain knowledge; constructing a question parsing Prompt template and using a large language model to analyze the structure of the original question to extract key entities from the original question; retrieving power domain knowledge in a hybrid similarity retrieval manner based on the sorted out power domain knowledge and the key entities extracted from the original question; obtaining database tables and data schemas related to the original question through a multi-level schema linking method; standardizing knowledge and designing a question enhancement Prompt template based on the retrieved power domain knowledge and the obtained data schema, and using a large language model to reconstruct and enhance the original question to eliminate confusion and interference factors and improve the accuracy of question answering.

The invention discloses an electrical equipment defect identification method and system based on large model tuning, and the method comprises the steps: obtaining multi-modal defect data, and carrying out the defect identification through combining a domain knowledge graph tuning large model; and predicting an evolution trend based on an identification result, and providing a maintenance decision. The system comprises a multi-modal sensing module, a knowledge construction module, a large model tuning module, a defect identification module, an evolution prediction module and a decision support module. According to the method, the completeness, accuracy and generalization ability of defect identification can be improved, evolution prediction is realized, an intelligent prospective maintenance decision is provided, the efficiency is improved, and the cost is reduced.

The invention discloses a training method of a generative language model based on retrieval enhancement and a dialogue generation method and device.The training method comprises the steps that data cleaning is conducted on original historical dialogues, a pre-trained first large language model and a pre-trained second large language model are constructed, the cleaned historical dialogues are input into the first large language model, and the second large language model is input into the second large language model; generating corresponding question description statements and reply statements; inputting the question description statement and the reply statement into a second large language model to generate a corresponding single piece of first knowledge, and then performing data screening to obtain screened data; n pieces of second knowledge retrieved in the database and the generated single piece of first knowledge form n + 1 pieces of knowledge corresponding to each high-quality historical dialogue, and mixed training data is constructed and obtained; and training the generative language model by using the mixed training data. The problems that the training data is difficult to obtain and the reply of the existing RAG system is not accurate enough can be solved.

The invention provides a life cycle evaluation automatic modeling method based on a large language model, and relates to the technical field of life cycle evaluation, and the method comprises the steps: extracting the multi-modal information of texts, tables, images and the like from the multi-source data of academic literatures, reports and the like, constructing an instruction data set in combination with LCA process knowledge, carrying out the instruction fine tuning of a base large model, and carrying out the automatic modeling of the life cycle evaluation. And obtaining the LCA field large language model. And generating a standardized prompt by utilizing a prompt word optimizer, driving a model to generate a product LCA model framework, filling list data, and perfecting process data in combination with semantic search and a correction mechanism. And intelligent connection recommendation among unit processes is realized by calculating the semantic similarity of input and output streams. And finally, the verified structured data is output to LCA modeling software, an automatic modeling process is completed, and the modeling efficiency and normalization are improved.

The invention discloses a knowledge intelligent analysis and question-answering method and system based on time sequence knowledge graph retrieval enhancement, relates to the technical field of natural language processing, and aims to solve the problem that a wrong answer is generated due to the fact that a model possibly retrieves semantic-related but time-inconsistent information due to a time-insensitive retrieval mechanism in an existing method. According to the method, a dynamic time sequence knowledge graph modeling and hierarchical interactive retrieval mechanism is introduced. According to the framework, entities and relationships are bound with specific timestamps through time annotation in a knowledge construction stage, and a dynamic graph capable of evolving along with time is formed; in a retrieval stage, through time query decomposition (decomposing a multi-time constraint complex query into single-time sub-queries, and gradually screening related knowledge by a three-layer interactive retriever (time sequence sub-graph retrieval, node-level retrieval and knowledge-level retrieval), time conflicts and redundant interference are reduced, and finally answers with consistent contexts and accurate time are generated.

The invention relates to the technical field of software development, and discloses a method for project process management and quality management through an intelligent agent, and the method comprises the steps: S1, carrying out the multi-protocol access, database direct connection, multi-modal analysis and context memory association enhancement of a communication office platform through an intelligent sensing layer; s2, constructing a dynamic knowledge graph through a knowledge construction layer, configuring a node state, and carrying out relation modeling; s3, an intelligent decision-making layer carries out deep analysis and reasoning through project related knowledge and relationships presented in the dynamic knowledge graph, and provides decision support for project management; s4, realizing data integration and visual report generation through a visual layer; through automatic data acquisition and information analysis, manual check of chat group information one by one is replaced, the project information arrangement time is greatly shortened, key information can be accurately identified and extracted through the intelligent agent, information omission or errors caused by negligence during manual arrangement are avoided, and the accuracy and integrity of project weekly report are ensured.

The invention relates to the field of target intention prediction, and relates to a target intention recognition method based on knowledge and data combined driving, and the method comprises the following steps: 1, collecting behavior variable data of an air flying target, and carrying out the data cleaning, thereby obtaining x; 2, expert knowledge is obtained through a Delphi method, and a confidence rule base is constructed; step 3, inputting the data into a confidence rule base module to obtain an embedded representation xe of expert knowledge, and splicing the embedded representation of the expert knowledge and the data to form lt; x, xegt; all the data are input into the neural network module; and step 4, iteratively optimizing parameters of the belief rule base and the neural network in a collaborative optimization mode until the model converges. According to the method, the effect of expert knowledge in the intention recognition process is fully utilized, and the accuracy of the model is improved. And high intention recognition accuracy can still be obtained under the condition that the data volume is not large.

The invention discloses a question answering system and a construction method for a motor vehicle driving teaching knowledge graph, and aims to overcome the defects of knowledge coverage integrity, scene adaptability, reasoning depth and interaction naturalness in the prior art. A traffic regulation document, coach voice and short videos and vehicle-mounted real-time data are integrated through a data acquisition module to cover rules and experience knowledge, a knowledge construction module constructs a space-time dynamic knowledge graph containing static and dynamic nodes based on Dgraph, space-time association is achieved by means of GeoHash coding, real-time updating is completed through an MQTT protocol, and the time-space dynamic knowledge graph is stored through a storage module. The intelligent reasoning module calls a DoWhy model to construct an'operation, principle and result 'causal chain in combination with a physical formula so as to output deep interpretation, and the interaction module achieves multi-mode immersion teaching through speech synthesis, gesture recognition and 3D animation, dynamically optimizes knowledge pushing according to student operation data, and achieves multi-mode teaching. The comprehensiveness, the real-time performance, the scientificity and the interaction naturalness of driving teaching are improved, and the method is suitable for intelligent driving teaching scenes.

The invention discloses a multi-dimensional capability construction knowledge tracking method based on learning behavior decoupling, and belongs to the technical field of knowledge tracking. The method comprises the steps of obtaining test question embedding and test question-response embedding, and obtaining learning deviation behavior characterization and multi-scale behavior characterization based on the test question-response embedding; inputting the learning deviation behavior representation and the multi-scale behavior representation into a binary state model to obtain a knowledge construction representation; obtaining a test question sequence structure representation based on test question embedding, and performing multi-scale association on the test question sequence structure representation to obtain a multi-scale test question association representation; the multi-scale test question association representation and the knowledge construction representation are subjected to student ability modeling through frequency domain perception fusion, and differential learning ability is obtained; and predicting the student test question performance based on the differentiated learning ability to obtain a student test question performance prediction value. The method improves the accuracy of student test question performance prediction.

The invention discloses a subject cognition teaching knowledge construction and intelligent navigation system based on a knowledge graph, and relates to the field of education technology and intelligent teaching. The knowledge graph construction module is used for extracting knowledge points and association relationships thereof from subject teaching resources and constructing a structured knowledge graph; the personalized cognitive state vector generation module analyzes the mastering degree of knowledge points by means of a cognitive diagnosis model, and generates a state vector reflecting the cognitive level of an individual; the navigation strategy generation module adopts a hierarchical reinforcement learning method, and dynamically generates a navigation strategy containing knowledge point priorities and an optimal learning path by taking a learning target as guidance; and after the learning effect adjustment module pushes the strategy to the learner, acquiring knowledge point mastering state deviation and learning strategy consistency deviation in real time, and synchronously updating the edge weight of the knowledge graph and cognitive diagnosis model parameters. According to the system, through dynamic evolution of the knowledge graph and self-adaptive updating of the cognitive model, accurate optimization of a teaching strategy is realized, and the personalized learning navigation efficiency is improved.

The invention discloses a hierarchical structured hyper-stereoscopic knowledge base construction method based on video semantic analysis, and relates to the technical field of knowledge base construction.The hierarchical structured hyper-stereoscopic knowledge base construction method comprises the steps that a stable ontology layer frame is generated through a first round of database construction mechanism, and multi-angle details are supplemented for nodes through a second round of database construction mechanism; according to the decoupling type process, common structure drift, concept redundancy and semantic omission in single-round extraction are effectively avoided, and high-quality and controllable knowledge construction is achieved. According to the method, the logic relation is marked for the same-layer nodes and the cross-layer nodes in the ontology layer framework, so that the whole knowledge base not only has the structural property, but also has the rich semantic linkage capability, and the reasoning and visualization effects are greatly improved. In addition, an inference rule is defined based on an explicit logic relationship, so that the knowledge base realizes advanced functions of same-layer recommendation, cross-layer navigation, causal tracing and the like.

The invention belongs to the technical field of artificial intelligence content generation, and discloses an AI GC-based multi-modal picture book material fusion and dynamic presentation method. The method comprises the following specific steps: S1, creating a picture book; s2, illustration matching generation; s3, audio production and addition; s4, preliminarily fusing the materials; s5, interactive logic design; s6, embedding AR elements; and S7, carrying out personalized customization recommendation. According to the method, knowledge picture books are generated by means of AI GC, multi-mode and AR assistance are achieved, abstraction is converted into images, learning potential is stimulated, and knowledge construction, personalized customization, special effect matching, AR and expansion imagination are assisted; a warm bridge is built with the parent-child, the parent-child explores the world together, multiple modes are achieved, AR rich interaction is achieved, the parent-child distance is shortened, the barrier is eliminated, and the parent-child is warm and sweet in light.

The invention discloses a thermal power plant intelligent question and answer method based on multi-source corpus fusion, and aims to solve the problems that knowledge construction depends on manual annotation, the corpus format is single, the context understanding ability is insufficient and the credibility of a generated result cannot be guaranteed in an existing question and answer method. The method comprises the following steps: introducing a vectorization processing mechanism and a semantic block model generation module to perform unified embedding and compression expression on various types of texts such as thermal power plant operation regulations, equipment manual, operation records and the like, so as to realize accurate retrieval and structured answering based on semantic correlation; and an answer judgment mechanism is introduced to reduce the risk that a language model generates an illusion phenomenon, so that the accuracy and interpretability of question and answer output are improved, and the intelligent question and answer requirements of operators in the aspects of equipment diagnosis, regulation query, accident handling and the like are met.

The invention relates to the technical field, and particularly discloses a big-data-based question and answer information processing method for AI online education, which comprises the following steps: S1, constructing a subject knowledge graph, taking concept nouns as large nodes, taking question solving methods as small nodes, establishing a derivation relationship between concepts, and forming a structured knowledge base; s2, processing questions of the user, identifying question knowledge points by extracting subject keywords, positioning activation nodes in the knowledge graph, and determining a derivation path; and S3, generating an answer text, generating a connection text according to a node sequence, and performing deviation detection and correction through real-time semantic vector comparison to ensure the answer accuracy and logic continuity. The whole process realizes a complete closed loop from knowledge construction to intelligent question and answer.

The invention discloses a multi-source document management method and device based on knowledge construction and fusion storage, and relates to the technical field of document management, and the method comprises the steps: receiving a multi-source document to an object storage system, and recognizing the document type; performing document analysis and structure extraction according to the document type; extracting pictures in the image-text mixed content, uploading the pictures to an object storage system, generating a mapping dictionary, and inserting picture marks in a text part of the mapping dictionary; carrying out structured processing on contents of the table key value pairs to extract summaries and abstracts; performing standardization processing and semantic slicing on the processed image-text mixed content, table key value pair content and / or plain text content to generate knowledge fragments; constructing a knowledge extracting questions from knowledge fragments; the knowledge fragments are stored in a first index, and the questions and IDs of the corresponding knowledge fragments are stored in a second index; generating vectors for each knowledge fragment and question, embedding and writing the vectors into a vector database; and performing document management based on the knowledge base. The document management efficiency is improved.

The invention discloses a vehicle refitting scheme generation method and system based on a large model and a knowledge graph, and relates to the technical field of electric vehicle networking, and the method comprises the steps: inputting an obtained user refitting demand text into a cloud large model, analyzing the refitting demand text, extracting key information, converting the key information into a query vector, and sending the query vector to a cloud server; the method comprises the following steps: establishing a vehicle refitting knowledge graph, performing matching retrieval with entity embedding in the commercial vehicle refitting knowledge graph, constructing cue words according to the retrieved knowledge, generating a vehicle refitting scheme through cloud big model thinking chain reasoning, calling a 3D component to render a scheme effect graph, and feeding back the scheme effect graph to the local; vehicle data, accessory data, scene data, law and regulation data and historical modification case data are obtained in advance, after data preprocessing, entities and relationships are obtained through named entity recognition and relationship extraction, a commercial vehicle modification knowledge graph is constructed, and entity embedding in the knowledge graph is obtained through graph neural network learning. According to the invention, a refitting scheme which better meets user requirements can be obtained.

The invention discloses a knowledge base construction method and system based on urban planning implicit knowledge deduction, relates to the technical field of urban planning, and aims to solve the problems that an existing planning knowledge base is insufficient in implicit knowledge mining, poor in scene adaptability and lack of dynamic optimization capability. The method comprises the steps of obtaining multi-source data and performing standardization processing to obtain an enhanced data pool; optimizing the large language model to extract explicit and implicit planning knowledge; constructing a planning knowledge association network with association strength; building an initial knowledge base containing classification, retrieval and implicit knowledge deduction units; generating an adaptability evaluation result through a multi-scene test; constructing a knowledge evolution rule based on an evaluation result and completing knowledge base iterative reconstruction; and establishing a real-time spatial data dynamic triggering mechanism to realize continuous optimization of the knowledge base. According to the method, accurate association and deduction of explicit and implicit knowledge are realized, the scene adaptability and dynamic updating capability of the knowledge base are improved, scientific and efficient knowledge support is provided for urban planning decision making, and the method is suitable for various planning scenes.

The invention discloses a financial field knowledge base construction method, device and equipment. The method comprises the following steps: firstly, identifying a text region, a table region and an image region from a target image; then extracting text data of the text region by using an OCR algorithm, and extracting semantic features and visual features of the image region and a second entity set and an entity type corresponding to the table region by using a multi-modal AI model; carrying out illusion detection by utilizing the similarity of the two entity sets, and when judging that the illusion of the AI model does not trigger a fault-tolerant mechanism by utilizing a detection result, carrying out intelligent alignment processing on the two entity sets, and screening out an optimal entity matching pair; carrying out formatting verification on the entity type; and then context knowledge association processing is carried out on text data corresponding to the text region, semantic features and visual features corresponding to the image region and entity matching pairs passing verification, and a more stable and accurate knowledge base is constructed by utilizing the obtained graph structure document to represent corresponding structured knowledge.

The invention discloses a power grid channel selection thematic spatio-temporal knowledge graph construction method and device and a power grid channel screening method and device, and the method comprises the steps: obtaining data information and expert knowledge related to power grid channels, constructing a power grid channel selection digital base based on the data information and the expert knowledge, and selecting a power grid channel selection digital base based on the power grid channel selection digital base. And constructing a power grid channel selection thematic spatio-temporal knowledge graph for power grid channel selection. Through the method and device provided by the embodiment of the invention, informatization expression, unified management query, efficient screening and intelligent reasoning classification analysis of power grid channel selection data can be realized, power grid channel planning and construction are supported, and compared with manual screening, the data screening efficiency is improved, the error rate is reduced, and the power grid channel selection efficiency is improved. And the labor intensity of engineers and decision makers is greatly reduced.

The present application discloses a method for constructing a knowledge chain library, a method for answering questions, and related devices and equipment. The method includes: obtaining the output result after a large language model learns from a knowledge point library; wherein, the output result at least includes the predicted relationships between knowledge points in the knowledge point library; based on the predicted relationships between knowledge points, obtaining a number of candidate knowledge chains; based on the large language model after learning from the knowledge point library, detecting the candidate knowledge chains to obtain the detection result of the candidate knowledge chains; wherein, the detection result includes whether the candidate knowledge chains are contradictory; based on the detection result of the candidate knowledge chains, determining whether to select the candidate knowledge chains as target knowledge chains and save them to the knowledge chain library. The above solution can improve the quality of knowledge construction, so as to improve the accuracy of question answering as much as possible even when assisting in answering complex questions.

The invention provides an API code optimization method and device based on a large language model and electronic equipment, and belongs to the field of software code optimization. The method comprises the following steps: constructing a knowledge construction module comprising a text collection unit, an extraction unit and a knowledge graph unit; a code sample is obtained through a text collection unit, and API architecture features of the code sample are extracted through an extraction unit; the API architecture features are stored in a triple form through a knowledge graph unit to form a knowledge base; extracting a to-be-retrieved API of the to-be-optimized code by using a knowledge retriever; obtaining a triple matched with the to-be-retrieved API and a corresponding explanatory text from a knowledge base to generate retrieval information; the retrieval information is converted into operable knowledge through a knowledge injector; and transferring the operable knowledge to the large language model, and generating and outputting a plurality of code optimization results. According to the method, the understanding capability of the large model on the API is enhanced, and the code optimization efficiency is improved.

The invention relates to the technical field of low-voltage prediction, in particular to a knowledge graph platform and method for low-voltage prediction in combination with deep learning, and the method comprises the steps: collecting and integrating the power grid topological data, equipment parameters, historical operation data and low-voltage response measure knowledge from a power grid business system and a customer service platform, constructing a structured low-voltage knowledge graph; based on the data set extracted from the low-voltage knowledge graph, training is carried out through a deep learning model, and a low-voltage prediction model is generated; an incremental learning process is periodically adopted, and the low-voltage prediction model is iteratively updated according to newly-collected power grid change data; and based on the iteratively updated low-voltage prediction model, predicting a target transformer area, and providing an alarm and a response measure according to a prediction result. Knowledge distillation incremental learning is adopted, it is ensured that the model has high prediction precision for historical and newly-added power grid states, and continuous and stable evolution of the model is achieved.