106 results about "Knowledge generation" patented technology

The invention relates to a method and a device for generating description-type judicial knowledge driven by judicial data. The method comprises the following steps: extracting legal concepts and / or legal terms from a legal text, and constructing judicial concept knowledge ontology based on the legal concepts and / or the legal terms; based on the judicial concept knowledge ontology, a judicial concept extraction model is constructed and trained, the judicial concept extraction model is used for generating descriptive judicial knowledge, and the descriptive judicial knowledge comprises specific vocabularies or phrases which have specific legal definitions and serve as judgment elements in judicial judgment. According to the embodiment of the invention, the description-type judicial knowledge can be accurately generated.

The invention relates to a question and answer method and system fusing a multi-granularity knowledge graph and a self-adaptive agent. The question and answer method comprises the steps of knowledge governance and extraction, knowledge generation and expansion, knowledge retrieval and management, and knowledge rule mining and self-adaptive retrieval. Through cooperation of the multi-granularity knowledge graph and the self-adaptive agent, questions of the user can be more comprehensively understood, and more relevant knowledge can be retrieved from the knowledge base, so that the question and answer accuracy is remarkably improved, and wrong answers are reduced. Meanwhile, the multi-granularity knowledge graph can support more complex knowledge application requirements such as reasoning and prediction, so that the application capability of the question and answer system is enhanced, and the question and answer system can process more complex question and answer tasks such as multi-round dialogues and multi-task question and answer.

The invention discloses a credibility evaluation method based on large model knowledge generation, and relates to the field of large model application and knowledge mapping, and the method comprises the steps: firstly, generating a plurality of natural language expression forms of a triple by using a large model; searching related literatures by means of a search engine, evaluating semantic similarity of the literatures and triads and credibility of source websites, and selecting high-quality related evidences; thirdly, credibility evaluation is carried out on dimensions such as the literature support degree, consistency and reliability of the triad and revenue evidence through a large model; and finally, fusing scores of multiple dimensions by using a multi-layer perceptron model, and generating a final confidence coefficient of each triple. The method can effectively combine the support degree of the literature, the reliability of the source and the potential reverse evidence, improves the credibility judgment accuracy of the knowledge, and is suitable for automatic credibility evaluation and verification of a large-scale knowledge base.

The invention discloses a global knowledge extraction method and system based on a large model and an RAG technology, and belongs to the technical field of large model data processing. According to the global knowledge extraction method and system based on the large model and the RAG technology, local sensitive hashing is adopted for duplicate removal, similar texts are combined through dynamic thresholds, and redundant data interference is reduced; a text segmentation strategy based on separator confidence ensures that segmented text blocks maintain semantic integrity and are adaptive to large model input length limitation, similarity retrieval and full-text retrieval are fused, results are reordered in combination with an RRF algorithm, semantic relevance and accuracy are considered, the multi-scene knowledge construction requirement is met, and the multi-scene knowledge construction efficiency is improved. High-correlation entity pairs are screened through mutual information, context knowledge is retrieved from a vector database in combination with an RAG system, semantic reasoning is conducted through a large language model, hidden logic relations among entities are generated, and jumping from data association to knowledge generation is achieved.

The invention discloses an ancient poetry multi-mode teaching system based on HSK classification, and belongs to the field of intelligent teaching. Comprising a learning evaluation portrait module, a learning path generation module, a physiological emotion monitoring module, a cognitive load analysis module, a vocabulary grammar enhancement module, a modal semantic analysis module, an artistic conception analogy generation module, a holographic scene generation module, a feedback interaction experience module, a content dynamic adjustment module, a recitation pronunciation correction module and an expansion knowledge generation module. A performance analysis feedback module and a review memory enhancement module; according to the method, learning tasks can be updated in real time along with the change of the ability of students, a one-step teaching mode is avoided, the learning efficiency and adaptability are improved, the learning experience and continuity are greatly improved, cultural faults can be effectively reduced, non-native Chinese language persons can understand the deep significance of ancient poetry more easily, and the learning efficiency is improved. The memory depth of the learner to the poetry artistic conception and vocabularies is greatly improved, and the learning motivation is also improved.

The invention discloses a fine-grained knowledge generation Agent method of an embedded metadata cue word project, and relates to the related technical field of data processing, and the method comprises the following steps: analyzing research problem generation elements, and determining research problem generation knowledge elements; constructing a knowledge element training data set; performing training fine tuning on the DeBERta model to obtain a fine-grained knowledge data set; constructing an embedded metadata cue word project; obtaining a research problem fine tuning data set; and carrying out fine tuning optimization on the large language model by adopting a LoRA fine tuning technology, and generating a research problem. The technical problems that in the prior art, due to the fact that model training is conducted based on a general data set, knowledge elements in a specific field are ignored, data are redundant due to the fact that fine-grained knowledge is not analyzed and screened, a language model is inaccurate, and the accuracy of a research problem generation result is poor are solved. The technical effect of improving the accuracy and quality of language model training and research problem result generation is achieved.

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 belongs to the technical field of medical education training systems, and particularly relates to a generative AI-based personalized infection control training system and method, and the system comprises a data collection module, a capability portrait construction module, a knowledge generation module, a difficulty regulation and control module, an evaluation module, a personalized learning module, an output module and a virtual patient interaction module. According to the system, user behavior data are integrated through a federal learning mechanism, a multi-dimensional ability portrait is constructed, hierarchical training content is generated by using a generative large model, and content difficulty dynamic adjustment is realized in combination with a Q-learning algorithm. The system supports VR / AR immersive training and voice interaction control, and can simulate a real infection scene and present a 3D propagation consequence. Compared with a traditional static teaching scheme, the system has higher adaptability, interactivity and training closed-loop ability, and the individuation and effectiveness of infection control training are remarkably improved.

The invention provides a named entity recognition method based on multi-modal large model fine-grained knowledge generation, and belongs to the technical field of information extraction in natural language processing. According to the method, a multi-modal large model MLLM and a large language model LLM are combined to jointly generate fine-grained auxiliary knowledge, the LLM uses a context learning mode to guide the LLM to generate auxiliary knowledge related to a sample, and the MLLM uses manual annotation data to perform fine tuning on the LLM, so that the MLLM outputs the related auxiliary knowledge according to input text and image information; and combining the obtained auxiliary knowledge with the original text, entering a downstream sequence labeling model for training and reasoning, and completing named entity recognition. According to the method, world knowledge and multi-modal information which are beneficial to information extraction are taken into consideration, the performance of named entity recognition of the downstream sequence marking model is improved, and the entities in the text can be recognized more accurately.

A multi-generation RAG process generates a first-generation prompt for input to LLMs. The first-generation prompt may specify a concept, raw data, and a first-generation request to draw inference of information related to the concept using the raw data. The process provides the first-generation prompt for execution by the LLMs and receives a first-generation response. The process iteratively updates the inference of information using the LLMs. The iteratively updating includes using the inference of information related to the concept that are received from a previous-generation response as contextual information for a subsequent-generation RAG process. The process receives a subsequent-generation response generated by executing the LLMs and stores the iteratively updated inference of information related to the concept for retrieval by the machine-learned language model.

The invention discloses a building industry multi-subject collaborative full life cycle carbon emission management system and method, and relates to the technical field of building industry carbon emission management. The system comprises a carbon perception and data collaboration module, a carbon simulation and deduction module, a carbon optimization and collaborative regulation and control module, a carbon accounting and auditing traceability module and a carbon decision and knowledge generation module. Multi-source heterogeneous data is converted into a carbon flow unit with time, space and responsibility subject attributes, data checking, locking and compliance sharing are achieved by means of a multi-subject data collaboration pool, carbon data barriers among all responsibility subjects are broken through, the problems of fragmentization of carbon data collection and lack of collaboration are solved, and the data collection efficiency is improved. And meanwhile, the carbon accounting and audit traceability module completes multi-dimensional accounting based on the carbon flow unit, and establishes a digital carbon chain pointing to an original data source and a responsibility subject, so that full-link traceability of carbon emission data is realized.

The invention belongs to the technical field of data structuring, and discloses an electronic medical record data structuring system based on a medical language model, and the system comprises a modular analysis module which is used for extracting an electronic medical record text and separating the electronic medical record text into medical text modules such as a main complaint module, a past history module and a current medical history module; the data annotation module is used for annotating the entities in each module and the semantic relationship between the entities; the deep learning model module is used for constructing a deep learning model for medical entity and relation extraction and training the model; and the structured knowledge generation module is used for obtaining the electronic medical record, analyzing the electronic medical record through a text data structured model after the electronic medical record is modularly analyzed, and generating a structured knowledge graph containing entity attributes and semantic relationships. According to the method, through modular design and specialized processing, the problems of medical text structure diversity, professional term complexity, data imbalance and the like are effectively solved, and the accuracy and efficiency of electronic medical record structuring are improved.

The invention discloses a knowledge-intensive task-oriented thinking chain prompt optimization method and system, and belongs to the field of natural language processing. When the model is used for reasoning knowledge-intensive tasks based on thinking chain prompts, the generated thinking chain often has the problems of knowledge missing, irrelevance, even errors and the like. Therefore, a prompt optimization process is improved in a manner of combining knowledge generation and knowledge evaluation, and a thinking chain prompt which more pays attention to knowledge quality is obtained, so that the knowledge integrity, correlation and correctness of a model generated thinking chain are improved. The knowledge generation means that the guide model explicitly generates knowledge fragments in the thinking chain; according to knowledge evaluation, a loss function containing answer accuracy and multi-dimensional knowledge indexes is designed, and gradient information of the loss function is utilized to select an optimal candidate word to update and optimize prompts. The system comprises a thinking chain knowledge generation module, a knowledge evaluation module, a candidate word initialization module, a candidate word gradient calculation module and a prompt updating module.

The invention discloses a multi-modal health knowledge generation and integration system, which is applied to the technical field of fusion and application of health data, and comprises a multi-modal data acquisition and preprocessing module used for acquiring multi-modal health data and preprocessing the multi-modal health data; the multi-level fusion framework design sub-module comprises data-level fusion based on a time alignment algorithm, feature-level fusion based on a Transform cross-modal attention mechanism and decision-making-level fusion based on an ensemble learning algorithm; and the intelligent knowledge generation sub-module comprises health knowledge graph construction based on a graph neural network, personalized health risk report and intervention scheme generation based on a conditional generative adversarial network, visual image feature contribution degree based on gradient weighted class activation mapping and text data key factor analysis based on an SHAP value. According to the method, the bottleneck of a data island is fundamentally broken through, and the generation quality and the application value of health knowledge are improved.

The invention discloses a retrieval enhancement generation method and system based on long-term memory and multi-source knowledge iterative fusion. The method comprises the following steps: firstly, after user inquiry is received, triggering long-term memory database retrieval, external knowledge base retrieval and large language model internal knowledge generation in parallel to construct a multi-source candidate knowledge base, and improving result correlation by adopting a self-adaptive retrieval method based on a dynamic top-k value; secondly, inputting user query and multi-source knowledge into the large language model for iterative fusion, and generating a final answer through conflict detection, fusion processing and confidence evaluation; and finally updating the long-term memory database. The method can improve the accuracy and stability of the generated answers in a multi-round interaction and complex task scene, reduces the risk of answer one-sidedness, inference incompleteness or fact deviation, enhances the multi-source knowledge utilization ability and long-term learning ability of the system, and improves the user experience. Therefore, the comprehensive performance and reliability of the system in applications such as intelligent question answering, information retrieval assistance and text generation are obviously expanded.

The invention discloses an electronic archive intelligent data management method and system based on a large model. The method comprises the following steps: firstly, acquiring an electronic archive file, performing unified access, identifying a text through an OCR (Optical Character Recognition) technology, and reserving original layout coordinate information; analyzing the document page by page to generate a page-level structured object containing text and position mapping; then, on the basis of a preset domain prompt template, calling a large language model to extract file metadata from the page-level object, recognizing entities and relationships in combination with file knowledge ontology, and generating a semantic triple containing an evidence source page number; and finally, fusing the metadata and the triple to construct an electronic archive knowledge graph with a page-level traceability function. According to the invention, through a whole-process semantic governance mechanism from access, analysis to knowledge generation, the problems of difficult analysis of unstructured data, weak semantic understanding and lack of traceability in traditional archive management are effectively solved, and the intelligent level and data credibility of archive governance are significantly improved.

The invention relates to the technical field of knowledge bases, and discloses a knowledge base processing method and system based on Internet of Things big data, and the method comprises the steps: constructing an initial knowledge base, collecting use records, generating a real-time knowledge generation strategy, generating real-time knowledge, and updating the knowledge base. The system corresponds to the method. According to the method, the real-time knowledge generation strategy is obtained by collecting the use record of the user for the initial knowledge base in real time, analyzing the characteristics of the use record and adjusting the initial knowledge generation strategy, so that the knowledge generation can meet the actual demand of the user, and the real-time knowledge generation strategy is utilized to process the real-time Internet of Things big data to generate the real-time knowledge and update the initial knowledge base. According to the method, dynamic updating of the knowledge base is achieved, timeliness and accuracy of the knowledge base are guaranteed, the problems that the knowledge base is not comprehensive in construction, not timely in updating and difficult to adapt to big data characteristics of the Internet of Things are effectively solved, and more accurate and effective knowledge support is provided for application of the Internet of Things.

The invention discloses a 6G-oriented cross-domain knowledge-driven network intelligent scheduling system and a 6G-oriented cross-domain knowledge-driven network intelligent scheduling method. The architecture comprises a cross-domain knowledge collaborative evolution module, a network closed-loop management module and a multi-normal-form learning decision module, the cross-domain knowledge collaborative evolution module is used for disassembling a network state into an environment domain, a network domain and a user behavior domain, and online incremental fusion of three-domain knowledge is realized through a graph neural network; dynamically updating the global knowledge base based on knowledge distillation; the network closed-loop management module is used for constructing a function closed loop of perception-reasoning-knowledge generation-decision issuing-verification optimization-memory retrieval; and the multi-normal-form learning decision module is used for fusing meta learning, reinforcement learning, federal learning and self-supervised learning to realize rapid migration and continuous evolution of the strategy. According to the method, the network data throughput, the fault recovery speed, the flow prediction precision, the resource fairness, the path efficiency and the task success rate are improved, and the method is suitable for complex 6G scenes such as air-ground integration and low-altitude traffic control.

The embodiment of the invention belongs to the technical field of dialogue questions and answers, is applied to a questions and answers knowledge processing scene, and relates to a questions and answers knowledge base updating method, device and equipment and a storage medium thereof.The method comprises the steps that questions and answers basic data sent by a multi-data source end are obtained and input into a data comprehensive processing component to be processed, and questions and answers promotion data are obtained; on the basis of question and answer promotion data, a question and answer knowledge generation component based on PingAnGPT is adopted to generate question and answer pairs, then the question and answer pairs are cached to a target question and answer knowledge base, updating of the question and answer knowledge base is completed, it is avoided that the question and answer knowledge generation component is directly adopted to sort question and answer basic data of a document class, an image class and a structural form class, and the question and answer knowledge generation efficiency is improved. The question and answer knowledge sorting and using efficiency is improved, different knowledge types such as forms, pictures and documents are processed in combination with the data comprehensive processing assembly, compatible processing of multi-carrier type data is achieved, and the multi-carrier type data source end can be effectively utilized for large-scale question and answer knowledge updating.

The invention relates to the technical field of large language models, and discloses a dialogue generation method based on exogenous knowledge generation potential sorting enhancement, which comprises the following steps: quantifying generation potentials of different knowledge fragments, and performing correction and normalization; constructing positive and negative sample pairs to perform data enhancement; a retriever is finely adjusted on the data enhanced training set; splicing a dialogue history and a previous set knowledge fragment with the highest correlation after a searcher sorts, and finely adjusting a generator; and the generator performs reasoning on the test set and returns replies generated according to the dialogue history and the recalled knowledge fragments. At present, a mainstream retriever more pays more attention to semantic correlation between dialogue history and exogenous knowledge, but does not have the ability of generating reply labels by combining the dialogue history with the exogenous knowledge. According to the method, the difference is considered in the searcher training, so that the knowledge set recalled by the searcher can better promote the generation task.

The invention discloses a domain knowledge content generation method and system based on retrieval enhancement generation, and belongs to the technical field of natural language processing and knowledge generation. Performing fuzzy semantic retrieval in the structured knowledge base to obtain semantic matching entries and calculate semantic relevancy; constructing a semantic fusion representation vector to form an enhanced representation set; performing context alignment with the query vector, and extracting a causal path fragment with the maximum weight; inputting the causal path and the query vector into a large language model, and executing a condition generation operation; analyzing and judging whether the generated content has term jump or logic chain scission or not based on the term dependency graph, if so, adjusting a context window and regenerating, and finally outputting professional content meeting dependency consistency; according to the method, the accuracy and logic consistency of professional field text generation are effectively improved, and the method is suitable for knowledge generation tasks in complex semantic scenes.

The invention provides an automatic attack path analysis and evaluation method and device based on a large language model, and the method comprises the steps: firstly, determining a to-be-analyzed system architecture, determining an attack entrance and an attack exit, constructing a tag tree, and extracting the target information of each tag node in the tag tree; analyzing a potential attack surface and an attack purpose of each tag node in the tag tree by using a large language model; obtaining domain knowledge corresponding to the to-be-analyzed system architecture, and generating an attack tree according to the target information of each label node, the corresponding potential attack surface, the attack purpose and the domain knowledge; and finally, evaluating the feasibility of the attack tree based on a large language model, scoring, and optimizing to obtain a target attack tree. According to the embodiment, the problems of subjectivity, updating difficulty, information abstraction and the like of a traditional threat database-based method are solved, and meanwhile, the method has cross-domain application capability and is suitable for various fields such as intelligent automobiles, intelligent ships, industrial equipment, unmanned aerial vehicles and aerospace.

The invention belongs to the technical field of hole part process decision and computer aided process design (CAPP), and relates to a body-based hole part geometric tolerance assessment method. The method is specifically realized through the following steps: step 1, constructing a knowledge generation ontology in the geometric tolerance assessment domain of the hole parts; 2, establishing an SWRL inference rule for geometric tolerance evaluation of the hole parts; 3, extracting part structure and surface information, and establishing assertion formula sets AC and AS; 4, extracting geometric tolerance specification information of the hole parts, and constructing an assertion formula set AG; and step 5, constructing an instantiated ontology knowledge base generated by geometric tolerance assessment domain knowledge of the hole parts, and reasoning the instantiated ontology knowledge base by using a reasoning engine according to the SWRL reasoning rule base to generate geometric tolerance eligibility of the hole parts.

The application discloses a brain map drawing electronic pen and a handwriting knowledge generation and database construction device and method, and relates to the technical field of knowledge generation and database construction, and specifically relates to a brain map drawing electronic pen and a handwriting knowledge generation and database construction device and method.

This disclosure relates to knowledge generation and implementation. A knowledge graph system comprises at least one processor, at least one database communicatively connected to the at least one processor, and a memory storing executable instructions. When executed, the instructions cause the at least one processor to aggregate data associated with a plurality of entities, the aggregated data reflecting one or more relationships between two or more of the plurality of entities. Attribute data identifying loan amounts, property values, and appraisal sources may be extracted from the aggregated data. A knowledge graph data structure may be generated having a plurality of subject notes corresponding to the extracted attribute information. Statistical distributions of attributes associated with one or more appraisal sources may be generated and an anomaly in a first statistical distribution may be detected based on a comparison of the first statistical distribution with a second statistical distribution.

The present invention provides a method, device, and robot for generating knowledge for solving applied problems, comprising: obtaining input text corresponding to a target applied problem input by a user; segmenting the input text into sentences and assigning a corresponding sentence number to each acquired text sentence; obtaining the noun content associated with each text sentence to form noun content recognition knowledge; and matching noun content extension knowledge associated with the input text from a pre-constructed knowledge base based on the noun content associated with each text sentence and its corresponding sentence number. The method, device, and robot for generating knowledge for solving applied problems provided by the present invention can generate noun content extension knowledge that is not contained in the applied problem itself but is of great value in solving the problem, thereby more effectively assisting the development of various systems related to applied problems and improving the accuracy of problem solving in various systems to a certain extent.

This application provides a method and system for dynamic knowledge updating of a large-scale model for operation and maintenance (O&M) technical services. It relates to the field of O&M technology, and models the knowledge generation triggering factors, iteration impact range, and knowledge association strength in multi-source O&M knowledge update sources to obtain a knowledge full-link evolution set including knowledge generation trigger records, iteration impact assessment results, and cross-knowledge association networks. Then, dynamic coupling rules are generated based on the real-time scenario characteristics of O&M tasks and this knowledge full-link evolution set. These rules are used to filter and integrate the knowledge full-link evolution set to obtain a scenario-coupled knowledge set. This set is embedded into the knowledge architecture of the large-scale O&M technical service model, and storage node parameters and retrieval logic are adjusted to obtain the basic updated model. Finally, the basic updated model is dynamically adapted in multiple dimensions, and the knowledge call priority sequence and storage node parameters are adjusted in conjunction with changes in scenario characteristics to generate an adapted updated model, thereby improving the adaptability of the large-scale O&M technical service model.

The application relates to a medical field knowledge fusion method based on label and content hierarchical fusion, and belongs to the technical field of knowledge fusion and artificial intelligence. Medical knowledge of different knowledge graphs is fused to construct a medical field knowledge base and provide large-scale medical industry knowledge services. The method comprises three steps of defining a meta label of an entity in a medical knowledge graph, data label alignment, and label content fusion. The method has the following characteristics: firstly, in the data label alignment, a data label alignment method based on integration of string measurement and semantic measurement is designed, and data label alignment is performed by using string features and semantic features. Secondly, in the label content fusion, a joint mechanism of content aggregation verification and unstructured knowledge generation is proposed, which aims to extract common knowledge of different granularities in different knowledge graphs, verify contradictory knowledge, and convert common triple knowledge into unstructured sentences to construct a medical knowledge base.

The invention relates to the technical field of natural language processing, in particular to an enhanced lightweight text classification data generation method and system based on a large language model, and the method comprises the steps: obtaining an original text data set; constructing a large language model agent interaction interface; executing data enhancement path processing to generate an enhanced data set; executing external knowledge path processing, and constructing an external knowledge base; based on the enhanced data set or the external knowledge base, training a lightweight text classification model; and outputting the trained lightweight text classification model. According to the method, through double-path parallel processing of the data enhancement path and the external knowledge path, the problem of semantic distortion and the problem of lack of lightweight model knowledge possibly caused by a traditional data enhancement method are solved; high-quality enhancement of text data and automatic acquisition of domain knowledge are realized by utilizing semantic comprehension and knowledge generation capability of a large language model; and meanwhile, the lightweight characteristic of the model is kept, and the method is suitable for resource-constrained environments.

The embodiment of the invention discloses a medical knowledge base knowledge generation method and electronic equipment. The method comprises the steps of determining a knowledge template of a medical knowledge base under the condition of obtaining input data; and obtaining a knowledge generation model, and according to the input data and the knowledge template, through the knowledge generation model, generating target knowledge to be stored in the medical knowledge base so as to store the target knowledge in the medical knowledge base. According to the technical scheme, the problem that the knowledge generation efficiency of the medical knowledge base is low can be solved.