18 results about "Deep knowledge" patented technology

The invention discloses an intelligent question bank retrieval and recommendation system based on an artificial intelligence knowledge graph, and relates to the technical field of artificial intelligence education. Comprising a knowledge graph construction module which is used for processing original education data and constructing a neighborhood knowledge graph comprising a hard preposition relation and a soft incidence relation; the user knowledge state graph construction module is used for constructing a user personal knowledge state graph isomorphic to the domain knowledge graph, and dynamically calculating a mastery index of each knowledge node through a deep knowledge tracking model based on user historical answer data; according to the method, by constructing the domain knowledge graph containing the hard preposition relation and the soft incidence relation, discrete knowledge points are organized into the structured network conforming to the cognitive law, so that the system can understand and follow the internal logic between knowledge, and a learning path which is clear in organization, efficient and coherent is generated.

The invention relates to the technical field of power dispatching, and discloses a knowledge distillation-based low-resource power big language big model training method, system and device and a medium, and the method comprises the steps: obtaining accident case data of the power industry, carrying out the problem construction and task setting, introducing a quality evaluation mechanism, carrying out the refusal sampling through a language model, and carrying out the training of a low-resource power big language big model. Generating a distillation data set for model distillation; introducing a LoRA module into the student model for fine tuning, constructing multi-source heterogeneous fine tuning data, and setting a training strategy to optimize the performance of the model; and performing training by adopting reinforcement learning, introducing language consistency rewards until the reinforcement learning achieves convergence on the reasoning task, and generating a final language large model. According to the method, through knowledge distillation and reinforcement learning, the deep knowledge and the reasoning ability of the super-large model are successfully migrated to the small model, so that the parameter quantity of the finally deployed model is greatly reduced, and the computing power resource required by reasoning is sharply reduced.

The invention provides an intelligent retrieval and reasoning generation method and system based on a knowledge graph and geoscience, and the method comprises the steps: firstly constructing a geoscience knowledge graph according to the information of a geoscience data set; secondly, identifying a key intention of the geographical question sentence; then, knowledge graph embedding work is carried out based on the entity relation structure of the knowledge graph, cross-entity potential relation and global information are captured, and reasoning from geoscience explicit data to deep knowledge is achieved; and finally, fusing a map result and a character result to carry out multi-domain retrieval so as to obtain an answer. Compared with an existing question answering system, the brand-new knowledge graph intelligent question answering system is constructed, the recall of answers can be improved, the knowledge reasoning ability is achieved, implicit internal association can be mined through explicit geoscience data, and geoscience experts can be helped to quickly and accurately find a target data set.

The invention provides an academic knowledge base construction method and system based on distributed crawlers and GraphRAG, and belongs to the technical field of computer information processing and knowledge management. The method comprises the following steps: constructing a distributed crawler architecture based on Selenium + Scrapy, completing character recognition and document logic structure reconstruction, storing a document as a Markdown format file, uploading the Markdown format file to a Dify knowledge base, segmenting the Markdown format file into knowledge blocks, and generating vector representation; extracting a semantic relationship between the entities, and constructing a knowledge graph according to the determined reasoning relationship; synchronously integrating the constructed knowledge graph and the segmented knowledge blocks into an intelligent agent, and constructing an intelligent agent process; by inputting a natural language question, an intelligent agent is triggered to execute semantic analysis, vector representation recall and knowledge graph reasoning, and an interpretable answer is returned. The problems that the data collection coverage rate is insufficient, text semantic conversion is distorted, deep knowledge association is missing, and knowledge base deployment is complex are solved.

The invention relates to a neural machine translation selective knowledge distillation method based on dependency constraint self-attention, and belongs to the technical field of machine translation. An existing knowledge distillation method has the problems that only vocabulary-level probability distribution is transmitted, syntactic structure constraints are ignored, and the capacity of a student model is reduced, so that the complex syntactic modeling capacity is insufficient. Therefore, according to the method, a syntactic matrix converted through a source language dependency syntactic tree is provided, linear combination is adopted to dynamically correct self-attention weight distribution of an encoder, and explicit syntactic constraints are synchronously injected into a teacher-student model. Through a selective distillation strategy of syntax perception, deep knowledge effective for training in a teacher model is screened, a cross-language syntax corresponding relation is obtained in combination with structure alignment distillation, and model compression and translation performance enhancement is realized through attention optimization and a selective knowledge transmission mechanism guided by a dependency syntax.

This invention discloses a zero-shot stance detection device and method based on multi-level knowledge selection, including a multi-level knowledge selection module and a zero-shot stance detection module. The multi-level knowledge selection module contains a knowledge selection model, which consists of an input layer, an encoding layer, a context layer, an attention layer, and an output layer. The knowledge selection model is used to match deep and shallow semantic information to obtain the deep knowledge required for zero-shot stance detection by extracting the interaction relationships between sentences and the interaction relationships between words in a single sentence. Knowledge, objectives, and arguments are input into the zero-shot stance detection module to complete the zero-shot stance detection, and the obtained deep knowledge is used as auxiliary information for zero-shot stance detection.

This invention provides a method and system for vertical domain adaptation based on entity knowledge distribution alignment, relating to the fields of natural language processing and artificial intelligence. First, by constructing entity knowledge representations from multi-perspective features of the same entity knowledge, this invention achieves a comprehensive and systematic characterization of the identity, structure, and semantic information of entity knowledge. Second, through a cross-perspective knowledge distribution alignment mechanism based on contrastive learning, it ensures semantic consistency of knowledge from different sources before fusion. Finally, by using a compression module based on learnable query tokens and precisely injecting the compressed knowledge tokens into the self-attention calculation of a specified layer in the encoder of a pre-trained language model, it achieves low-intrusive deep knowledge injection, enabling the pre-trained language model to adaptively coordinate internal and external knowledge without modifying the main parameters, significantly reducing the cost of vertical domain adaptation.

The invention discloses a recommendation question generation method and recommendation question generation equipment, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a user question; the user questions are converted into vectors, the vectors are matched with vectors in a preset recommendation question vector library, target vectors are obtained, and the recommendation question vector library comprises vectors obtained by converting the first candidate recommendation questions; each first candidate recommendation question is generated by a preset first intelligent agent based on a preset first prompt word and each knowledge text block in a preset knowledge text block set, and the first prompt word is used for prompting the first intelligent agent to generate a question to be recommended to the user according to the knowledge text block; and determining a recommendation question for output according to the candidate recommendation question corresponding to the target vector. According to the method, the professional degree and the accuracy of the generated recommendation problem are improved, so that the user is effectively guided to carry out deep knowledge exploration.

The present disclosure relates to the technical field of artificial intelligence education, and discloses a lightweight knowledge tracking method and system, which comprises the following steps: obtaining learning data input by a user, and performing natural language understanding and processing on the learning data through an LLM distillation module to determine learning resources for the learning data; wherein the learning data comprises text data and structured data; obtaining historical learning data of the user, and performing deep learning algorithm analysis on the historical learning data through a DKT module to predict the mastery of knowledge points by the user; and determining a learning task based on the learning resources and the mastery. By combining the large language model distillation technology (LLM distillation module) and the deep knowledge tracking technology (DKT module), the present disclosure can accurately track the mastery of knowledge points by students while reducing the computational complexity, and can realize personalized learning task recommendation, thereby effectively improving the learning effect.

The application discloses a cognitive state-based knowledge point-by-knowledge point differentiated decoding parameter injection method and system, belongs to the technical field of education, and is suitable for an adaptive personalized content generation scene. The method outputs a learner's mastery probability vector of each knowledge point through a deep knowledge tracking model, calculates a recent development area score in combination with a knowledge graph preposition dependency relationship and a knowledge point hierarchical depth; generates a local decoding parameter tuple for each knowledge point through a cognitive parameter mapping function, including a decoding temperature, a generation granularity and a scaffold insertion probability; and dynamically switches decoding parameters according to the mastery degree of the current knowledge point in the text generation process, realizes fine-grained step-by-step deduction in a low-mastery-degree area and summarization rapid passing in a high-mastery-degree area in the same text. The method realizes single-text knowledge point-by-knowledge point partition differentiated generation for the first time, introduces a cognitive transition section mechanism to process the mastery degree jump, effectively reduces the reasoning power consumption of an online education platform and improves the learning effect.

A system and method for using retrieval-augmented generation (RAG), in a large language model (LLM) having additional content to enhance relevance of LLM generated content. In operation, a user asks a question and the LLM determines whether additional content needs to be retrieved from a data management system to answer the question. If so, the LLM is provided with the user question and said additional content and asked to score its ability to confidently answer the question with the provided content. If the score is below a predefined threshold, the LLM is instructed to generate an alternate response using the retrieved additional content. Additionally, the system generates follow-up suggestions to assist the user in gaining more in-depth knowledge on the subject at hand. If the score is below a predefined threshold for a selected suggestion, the system will record this to assist to fill gaps in available content.

This invention discloses a deep knowledge tracking method based on graph neural networks, belonging to the field of smart education. Specifically, the method involves: first, cleaning the real dataset and storing the binary relationship between questions and skills in each interaction data point in a dictionary. Then, for the same student, all their questions are sequenced in ascending time steps, and corresponding exercise sequence graphs and interaction sequence graphs are generated based on the binary relationships. Next, a corresponding graph neural network is constructed to obtain the representation of each graph in the exercise sequence graph and interaction sequence graph. The exercise graph representation at time step t+1 is concatenated with the interaction graph representation at time step t, and the student's learning result at time step t+1 is predicted using a fully connected neural network. Finally, the graph neural network is embedded into an existing Transformer model, and parameters are updated through backpropagation. This invention achieves dynamic graph representation of questions and interaction sequences and utilizes an attention mechanism to update the knowledge state, improving the model's performance and interpretability.

The application relates to a deep knowledge tracking method and system applied to multi-element programming exercises, which comprises the following steps: receiving user exercise data and compilation log data of a programming platform system, and performing data preprocessing; performing log mode clustering on error information; constructing an exercise type feature matrix; performing position coding based on a time interval and learning ability; performing one-hot coding transformation on an answer interaction sequence to obtain an answer interaction embedding vector; and inputting the answer interaction embedding vector into a trained deep knowledge tracking model to realize deep knowledge tracking. Through data processing, knowledge base establishment and model improvement, the model can be applied to multi-element exercises, is more suitable for actual scene application, and especially through establishment of a compilation result knowledge base, application of knowledge tracking to various different exercise types in the programming platform field is realized.

This invention discloses a deep knowledge tracking method and a question recommendation method that integrates multiple features. The deep knowledge tracking method includes the following steps: S01. Pre-training an initial question representation vector matrix by inputting the absolute difficulty matrix of the questions and the similarity relationship between questions; S02. Using the student's answer interaction sequence set and the pre-trained initial representation vector matrix as input, constructing a student answer interaction sequence matrix, a historical relevance matrix, and a multi-knowledge point answer accuracy matrix, and concatenating them to form a comprehensive information matrix, which is then passed through a gating mechanism GLU to obtain the G matrix output; S03. Extracting the student's learning state matrix from the G matrix using multiple one-dimensional convolutional layers; S04. Obtaining the prediction result of the relative difficulty based on the question representation vector to be predicted and the learning state matrix. This invention has the advantages of simple implementation, high prediction accuracy and efficiency, and the ability to effectively handle questions of multiple knowledge points simultaneously.

The application discloses an integrated kitchen auxiliary design optimization method based on a household knowledge graph. The steps include: constructing an integrated kitchen auxiliary design model based on a household knowledge graph; inputting a preset interactive command into a kitchen design knowledge retrieval system, and the kitchen design knowledge retrieval system extracts a plurality of integrated kitchen knowledge points from the household knowledge graph in the integrated kitchen professional field according to the preset interactive command to perform auxiliary design and generate an integrated kitchen design scheme diagram, and then stores the integrated kitchen design scheme diagram in a data analysis and management system, so that the integrated kitchen auxiliary design optimization is realized. The application effectively solves the problems of poor kitchen household design scheme quality, serious homogeneity and the like, solves the problems of lack of shareable resources and low knowledge reuse efficiency in the kitchen professional field, supports deep knowledge association and mining of the integrated kitchen, generates an intelligent auxiliary design scheme, reduces the number of repeated design iteration modifications, and solves the problem of low household knowledge retrieval efficiency in the current integrated kitchen professional field.

The application relates to the technical field of artificial intelligence, can be applied to business scenes such as medical health, financial technology and cultural research, and discloses a content generation and optimization method based on a knowledge graph, which comprises the following steps: constructing a multi-source knowledge database, extracting core concepts and knowledge content, constructing a knowledge graph, performing semantic analysis to generate semantic vector representation and a keyword list; retrieving associated text segments based on the semantic vector and the keyword list, inputting an initial answer content generated by a generation model; matching field entities and knowledge graph nodes by using the knowledge graph, generating a logical reasoning path, optimizing the initial answer content, and generating final answer content. The application realizes precise retrieval, deep knowledge association and content generation with enhanced logical reasoning by fusing a multi-source knowledge database, knowledge graph reasoning and generation optimization; the precision of knowledge acquisition is improved by combining semantic vector matching and keyword retrieval; and the answer logic is coherent by constructing a knowledge graph reasoning path.

The invention discloses a question and answer method and device, equipment, a storage medium and a program product. The method comprises the steps of obtaining question description content; a retrieval result matched with the problem description content is retrieved from a pre-constructed operation and maintenance knowledge chain, the operation and maintenance knowledge chain comprises knowledge chain nodes and logic association between the knowledge chain nodes, and the knowledge chain nodes are determined according to a core entity in a standard operation and maintenance knowledge text; the logic association between the knowledge chain nodes is determined according to the entity relationship between the core entities; and according to the retrieval result, determining a question and answer result corresponding to the question description content. According to the method, the structured operation and maintenance knowledge chain which is pre-constructed according to the standard operation and maintenance knowledge text, is matched with the operation and maintenance scene and has logic association is retrieved, so that the accuracy and efficiency of knowledge extraction are improved, and deep knowledge reuse can be quickly and accurately realized; the intelligent level and the knowledge utilization efficiency of operation and maintenance of the power equipment are improved, and the operation reliability of the power equipment is improved.

The application discloses a layered enabling foreign language teaching video anchor point interaction method, and at least two layers of videos can be recorded when a teaching video is recorded, a first layer is a main teaching video, and a second layer is an auxiliary teaching video; wherein, at least a part of shallow knowledge points can be omitted in the main teaching video, and deep knowledge points are directly explained. In the scheme, the length of the main teaching video is short because the explanation of the shallow knowledge points is omitted, and the content is concise. For students with good foundation, only the main teaching video can be watched and learned, and the learning efficiency is high. For students with poor foundation, when the teaching video plays to the shallow knowledge point (i.e. the first knowledge point), if the student has doubts about the shallow knowledge point and cannot understand the deeper knowledge points built on the basis of the shallow knowledge point, the student can learn the explanation video of the shallow knowledge point in the auxiliary teaching video, which can facilitate the learning of the subsequent deep knowledge points, and the student can learn more deeply.