53 results about "Knowledge classification" patented technology

The invention provides an AI auxiliary reading method and system based on dynamic partitioning knowledge classification self-verification, and relates to the technical field of artificial intelligence, the method comprises the following steps: carrying out dynamic semantic partitioning on a super-long text to obtain a plurality of initial text units with consistent internal semantics; performing topic model construction according to the initial text unit and a layered Dirichlet process to obtain a topic distribution tag; receiving a user query request, and extracting a retrieval text set according to the hierarchical retrieval strategy and a retrieval text corresponding to the user query request; inputting the constraint cue word extracted by the topic distribution tag corresponding to the retrieval text set, the retrieval text set and the retrieval text into a text generation model to output a to-be-calibrated text; if the error scoring function of the to-be-calibrated text and any initial text unit in the retrieval text set is smaller than a preset error threshold value, the to-be-calibrated text serves as a credible text to be output to a user. According to the invention, the credibility and accuracy of the answer can be enhanced.

The invention discloses a knowledge retrieval method based on a multilayer index, which comprises the following steps of: obtaining a knowledge base of corresponding classification according to a knowledge retrieval statement in combination with a knowledge classification label; obtaining a plurality of retrieval target documents through vector similarity analysis according to the knowledge retrieval statements in combination with the document abstracts in the knowledge base of the corresponding classification; and obtaining a plurality of similar text blocks through vector similarity analysis according to the knowledge retrieval statement in combination with the text blocks of the plurality of retrieval target documents, and outputting the similar text blocks as knowledge retrieval. According to the method, a three-layer index structure containing knowledge classification tags, document abstracts and text blocks is constructed, the classification tags are dynamically matched through a large language model to reduce the retrieval range, high-correlation documents are rapidly positioned in combination with document abstract vector similarity analysis, and context logic relations are reserved based on text block hierarchical vector matching. The problems of fuzzy classification, low efficiency of document recall and context breakage in the traditional technology are solved, and accurate retrieval from macroscopic to microscopic is realized.

Provided herein is a novel method named Knowledge-Constrained Tree Search Decoding (KCTS) is provided, which is a first discriminator-guided constrained decoding approach to knowledge-grounded generation. The KCTS method also employs a Monte-Carlo Tree Search decoding (MCTS) instead of conventional LM decoding methods, which re-orders each token's importance based on the estimated future faithfulness starting from that token with multiple simulations. Coupled with a novel token-level hallucination detection method, RIPA (Reward Inflection Point Approximation), trained to predict the starting point of the hallucinating token, enabling effective adaptation of the knowledge classifier defined on the sequence level to the token level, this novel method is able to greatly mitigate hallucination problems of LLMs without the need of fine-tuning, thereby preventing the incurrence of high computational costs.

A smart contract fine-grained vulnerability detection method based on expert knowledge comprises the following steps: S1, constructing cue words by using a large language model, analyzing smart contract source codes, and labeling a smart contract data set; the method comprises the following steps: statically analyzing an intelligent contract source code statement, representing a source code element as a vector to obtain a source code fine-grained feature preliminary representation, and merging abstract syntax tree sub-trees into a code graph of a control flow graph node to obtain a graph representation of a source code; s2, acquiring heterogeneous code features and source code fine-grained features of the same smart contract, inputting the heterogeneous code features and the source code fine-grained features into a BGSCVul model for iterative fusion, and constructing a deep learning classifier; s3, by constructing an expert knowledge classifier, making a decision for specific expert knowledge; and S4, fusing the output of each sub-classifier by using a stack pressing method, and outputting final prediction.

The invention discloses a method for constructing a cultural relic knowledge organization, expression and characterization model for a Song charm theme. The method comprises the following steps: S1, constructing a knowledge classification system according to Song charm Shaoxing cultural relic types; s2, modeling knowledge entities and association thereof by using a semantic network; and S3, performing semantic representation of entities and relationships by using the multi-modal data. According to the method, systematic classification and semantic association of cultural relic knowledge are realized, and the structured level of cultural relic data is improved; the accuracy of knowledge reasoning and recommendation is improved, and intelligent service capability is provided for related fields of cultural relics; cross-medium and multi-dimensional knowledge integration and expression are supported, and technical support is provided for research and propagation of cultural heritage; meanwhile, the method is high in universality and can be popularized to other cultural heritage protection scenes, and wider value application is achieved.

The invention provides a dangerous large project special construction scheme AI auxiliary compilation system knowledge system construction and retrieval method, which comprises the steps of S1, multi-dimensional knowledge base construction: constructing a multi-dimensional knowledge base for storing dangerous large project compilation rules, specification standards, enterprise standards and project knowledge; s2, establishing a multi-level knowledge graph, establishing the dangerous and large project construction multi-level knowledge graph, and enabling the multi-dimensional knowledge base to form a knowledge system; s3, intelligently analyzing the multi-type documents; s4, knowledge management system construction, wherein the construction steps comprise knowledge classification; importing knowledge; automatic label prediction; and S5, constructing a multi-level knowledge representation and retrieval model. According to the method, on the basis of fully researching the current situation of scheme compilation, the knowledge characteristics in the building field and the bottleneck of the current large language model, the targeted knowledge system construction and efficient retrieval method is realized, and the technical problems of knowledge system construction and efficient retrieval and utilization of the AI auxiliary compilation system for the special construction scheme of the dangerous and large project are solved.

The invention relates to a charging intelligent customer service industry knowledge base updating method and device based on online feedback, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring service object feedback information received by a charging intelligent customer service system; obtaining a knowledge base feature set corresponding to each industry knowledge base associated with the charging intelligent customer service system; the knowledge base feature set comprises at least one of a keyword set, a knowledge classification tag and a typical question library; according to the knowledge base feature set corresponding to each industry knowledge base, matching the service object feedback information with each industry knowledge base to obtain a matching result; and under the condition that the matching result indicates that the target industry knowledge base matched with the service object feedback information exists in the industry knowledge bases, updating the target industry knowledge base according to the service object feedback information. By adopting the method, the updating accuracy of the industry knowledge base in the charging intelligent customer service can be improved.

The invention provides a low-resource scene hot word enhancement method and device based on synthetic data, and the method comprises the steps: extracting a scene hot word list of a target scene corpus, and defining a generation task based on the knowledge classification of the scene hot word list and / or a target scene; generating a sample text set based on the first large language model application scene hot word list and the generation task; and synthesizing a sample audio set of the sample text set, and training the initial speech recognition model by taking the sample audio set as training data and the sample text set as a label to obtain a hot word recognition model. According to the method provided by the invention, a generation task is obtained based on knowledge classification of a scene hot word list and / or target scene definition; obtaining a sample text set based on the first large language model application scene hot word list and the generation task; and the sample audio set of the sample text set is synthesized, so that efficient, high-quality and diversified sample data generation in the target scene is realized, and the hot word recognition accuracy of the hot word recognition model in the target scene is greatly improved.

The invention discloses a deep learning model-based knowledge learning agent training method, and relates to the technical field of auditing, and the method comprises the steps: carrying out the optimal disassembly task classification through a multi-model fusion knowledge classification method, and obtaining defined auditing knowledge and undefined auditing knowledge; optimal disassembly task classification is carried out by using a multi-model fusion knowledge classification method, and undefined audit knowledge is analyzed through an adaptive improved iteration mechanism, a fusion NLP algorithm and a deep learning audit agent to generate a question answer; the data security in the use process of the audit knowledge learning agent is controlled through a dynamic authority control and question and answer tracing mechanism; when facing large-scale and multi-level auditing tasks, the system can quickly position the core of a problem, redundant operation is reduced, and the response speed is increased.

The invention discloses a multi-source information fusion retrieval method and system combined with an information credibility portrait, and belongs to the technical field of intelligent information retrieval and auxiliary decision making. The method comprises the steps that the credibility portrait is constructed according to a predefined credibility index, and multi-source knowledge classification is completed; obtaining a candidate knowledge point set corresponding to query, and dividing the candidate knowledge point set into contrast knowledge point groups for conflict detection; according to a conflict detection result, performing complementary enhancement on the contrast knowledge point group without conflicts according to multi-source knowledge classification to form a fused knowledge point set; according to multi-source knowledge classification, credibility dynamic weighted fusion and human-in-loop conflict recheck and correction are carried out on the contrast knowledge point groups containing conflicts, and after conflict resolution is completed, a fused knowledge point set is obtained; and using the fused knowledge point set as a basis to feed back a retrieval result corresponding to the query. According to the method, the credibility of retrieval and decision results can be improved by utilizing the multi-source information through credibility enhancement and conflict resolution of the multi-source information.

The invention relates to a power enterprise knowledge question and answer retrieval enhancement method and equipment based on a knowledge classification system and a knowledge graph. The method comprises the following steps: constructing a power knowledge classification system according to the property and work content of a power enterprise; determining knowledge classification codes of the knowledge files according to the system; constructing a knowledge graph based on the knowledge file and the knowledge classification code thereof; determining a slicing strategy of each knowledge file according to the knowledge classification codes of the knowledge files, slicing the knowledge files into text blocks according to the slicing strategies of the knowledge files, extracting keywords from the text blocks, and constructing a keyword clustering tree according to the keywords; when question information of a user is received, querying a target keyword related to the question information in the knowledge graph; retrieving the problem information and a target text block related to the target keyword in the keyword clustering tree; and calling the power knowledge large model to generate answer information according to the question information and the target text block. The comprehensiveness and accuracy of the answer information generated by the enterprise brain during knowledge questioning and answering can be improved.

This application relates to a method, apparatus, device, and medium for constructing a test set based on a multimodal knowledge tree. The method includes: acquiring industry seed prompts, text data, and scene data; constructing a hierarchical industry knowledge tree and a seed question-and-answer set mapped to the industry knowledge tree based on the industry seed prompts, text data, and scene data; performing knowledge classification-guided instruction evolution processing on the seed question-and-answer set based on the industry knowledge tree to generate an evolved question-and-answer set, and attaching data traceability information to each question and answer in the evolved question-and-answer set; setting verification interruption points after the generation of the industry knowledge tree and after the instruction evolution processing, and verifying the industry knowledge tree and the evolved question-and-answer set according to manual verification instructions to obtain the target multimodal benchmark test set. This application improves the efficiency of benchmark test set construction, eliminates the need for manual data construction, reduces construction costs, and enables the construction of large-scale multimodal benchmark test sets.

The application provides a micro-class teaching method and system, wherein the micro-class teaching method comprises the following steps: constructing a knowledge classification database; obtaining the demand of a target object and determining the course content according to the demand of the target object; carrying out knowledge point keyword extraction and scoring on the course content, forming an index item with scores and adding the index item to the knowledge classification database, and establishing the association between the knowledge classification database and the teaching courseware; obtaining the target explanation knowledge point from the course content and obtaining the first teaching information, the second teaching information, the third teaching information and the fourth teaching information according to the target explanation knowledge point; and sending the final teaching information to a specified position after obtaining the final teaching information according to the first teaching information, the second teaching information, the third teaching information and the fourth teaching information. The application can meet the demand of students in different situations and improve the learning efficiency of students.

This invention discloses a method and system for generating real-time content in a specific domain based on AI technology, belonging to the field of artificial intelligence technology. The method includes the following steps: 1. Constructing a local material knowledge base RAG_src in the form of word vector storage using AI technology, whose materials include multimodal materials such as text, voice, audio / video, or H5; 2. Constructing a local domain knowledge classification knowledge base RAG_policy in the form of file storage using AI technology, whose content includes domain specification documents and technical classification documents categorized by domain knowledge and information; 3. Constructing PageIndex by combining a Large Language Model (LLM) with RAG_policy; 4. Receiving content generation requests from real-time software, calling RAG_src and PageIndex through LLM to generate real-time content that meets the requirements of the corresponding scenario; 5. Checking the generated content and outputting compliant content. This invention solves the problems of non-standard content generation, disconnection from relevant standards, low reuse rate of proprietary materials, and low retrieval efficiency in existing technologies, achieving accurate, efficient, and real-time content generation. It is adaptable to various scenarios such as real-time content generation, content compliance checking, and real-time domain assistance in specific domains. Application scenarios include, but are not limited to, oral practice and oral examinations according to teaching syllabi.

The invention discloses an open vocabulary target detection method based on prototype library feature mining, electronic equipment and a storage medium, which improve the detection performance of new category targets, and comprises a category generalization regional proposal network CG-RPN and a category specific knowledge distillation method CSKD, and comprises the following steps: 1, preprocessing a to-be-detected picture, sending the preprocessed to-be-detected picture and the corresponding picture level label into a visual language model (VLM); 2, performing feature extraction and feature fusion on a to-be-detected picture by the VLM, and sending an obtained feature map into the CG-RPN; the CG-RPN screens sample frames according to the features, allocates labels to the sample frames according to the classification scores and sends the labels to CSKD; 3, the CSKD respectively uses RoI head and VLM image encoder to process the sample frame into two groups of features, and then uses a category-specific knowledge distillation method to transfer rich visual semantic knowledge from the VLM; and 4, the classification head and the regression head obtain a final prediction result according to features generated by the RoI head, and correlation loss is calculated by GT and is reversely propagated to VLM to adjust parameters.

The invention discloses a dynamic construction method and device for fusing a hypertension prevention and treatment knowledge system based on double theories, can systematically solve the core problems of knowledge organization, classification and iteration, and constructs a hypertension prevention and treatment knowledge system with theoretical support, precise classification and dynamic iteration by fusing Bauer double view and Anderson four-level classification theories. The method comprises the following steps: (1) performing knowledge double-view disassembly based on a Bauer health development model; (2) performing knowledge four-level classification mapping based on an Anderson knowledge classification theory; and (3) constructing a knowledge system dynamic update closed loop.

The invention discloses a water conservancy knowledge base and intelligent question and answer construction method based on a large model and RAG, and the method comprises the steps: 1, combing a water conservancy knowledge system, and sorting water conservancy professional documents and data as materials of the knowledge base; step 2, constructing a water conservancy knowledge library management system through a J2EE system, a B / S architecture and a distributed object storage system; step 3, based on the RAG technology, forming different knowledge bases according to the sorted knowledge classification and confidentiality security level of the water conservancy industry, and establishing a water conservancy knowledge intelligent question-answering system on the knowledge bases; 4, performing extended application on the basis of the constructed water conservancy knowledge intelligent question-answering system; the problems that in the prior art, due to the fact that unstructured data processing is weak when a water conservancy knowledge base is constructed, a large number of image-text mixed documents such as PDF and PPT cannot be effectively utilized, and the recall rate and the accuracy rate are not high are solved.

1. Name of the product in this design: Graphical User Interface (Business Knowledge Guide) for Water Resources Business Analysis and Management System for Electronic Equipment. 2. Purpose of this design: An electronic device. 3. The key design feature of this product is its graphical user interface. 4. The image or photograph that best illustrates the design's key features: the front view. 5. Uses of the graphical user interface: for building a learning system for project-related knowledge, evaluating work statistics, compiling and querying information on honors and awards, and assisting in work. 6. Human-computer interaction method of graphical user interface: Click "Knowledge Map" in the upper left corner of the main view to enter the interface change state diagram 1, which can view mind maps of various knowledge categories. Clicking "Add Knowledge Category" on the upper right of the interface change state diagram 1 will take you to the interface change state diagram 2. This interface allows you to add a root node. By entering information such as "Knowledge Title", "Sorting" and "Knowledge Content Type", you can add a new knowledge category. In the interface, "XXX" represents text, numbers, letters, or symbols.

The application relates to the technical field of education training, and discloses a training subject management method and system based on knowledge classification. The system comprises a knowledge classification unit, a knowledge evaluation unit and a matching management unit. Through unique algorithms and technologies, knowledge is accurately divided into three types, namely, basic knowledge, advanced knowledge and application knowledge. For example, basic knowledge is compared by using a keyword library, advanced knowledge is constructed to calculate a correlation degree, and application knowledge is analyzed in combination with actual cases, thereby laying a solid foundation for subsequent training. A standardized evaluation process is designed for different types of knowledge, and the knowledge level of a trainer can be comprehensively understood. Different recommendation strategies are formulated according to the level of each knowledge type of the trainer, for example, excellent basic knowledge is focused on advanced and application knowledge, and large projects are recommended for excellent application knowledge, so that the learning needs of different trainers can be met, the problem of mismatched learning content is avoided, the training effect and efficiency are improved, and the knowledge and application ability of the trainer is more efficiently improved.

The invention discloses a knowledge learning method and device of an intelligent agent, electronic equipment and a computer readable storage medium, and belongs to the technical field of artificial intelligence. The knowledge learning method comprises the steps of receiving dialogue information; performing knowledge classification according to the dialogue information to obtain any one or more of concept type knowledge, scene type knowledge, shape type knowledge and skill type knowledge; respectively storing and updating each type of knowledge according to different types of knowledge; wherein the concept type knowledge is stored in a network ontology language form; the scene type knowledge is stored in an analytic graph form; shape type knowledge is stored in a picture form; skill type knowledge is stored in a text form. In this way, efficient knowledge management and updating can be achieved, and therefore the learning ability and intelligence of the intelligent agent are improved.

The invention provides a zero sample curriculum knowledge extraction and filtering method and device and electronic equipment, and the method comprises the steps: carrying out the blocking processing of a text of a to-be-processed teaching material, extracting knowledge points, obtaining a knowledge point hierarchical structure, carrying out the filtering of the knowledge points in the knowledge point hierarchical structure through reasoning judgment, and obtaining a zero sample curriculum knowledge extraction and filtering result. Obtaining a filtered knowledge point hierarchical structure; and based on a predefined knowledge type, classifying and marking the knowledge points in the filtered knowledge point hierarchical structure. According to the method, the integrity of the context is ensured through an iterative semantic partitioning strategy, a large model is guided to extract knowledge points of a hierarchical structure from a teaching perspective, low-quality contents are effectively filtered, and the teaching expressive power of a graph structure is further enhanced through semantic knowledge classification.

The invention relates to a patent classification method, a patent classification model training method and electronic equipment, and the method comprises the steps: constructing a first cue word which comprises the patent information, expert knowledge, classification standards and a first chain type classification thought of a to-be-classified first patent; and taking the cue word as the input of a pre-trained classification large model, and enabling the classification large model to analyze the patent information of the first patent by using expert knowledge and a classification standard based on a first chain type classification thought so as to obtain a classification result of the first patent. According to the method, the cue word is constructed based on chain thinking, so that the model can better learn and use expert knowledge and classification standards based on a chain classification thought, and the accuracy of a classification result is improved.

This invention discloses a method for autonomous decision-making and execution of robot tasks, comprising the following steps: classifying and constructing robot-related knowledge, including static knowledge and dynamic knowledge; expressing different categories of knowledge in different forms based on static and dynamic knowledge to construct a multi-level multimodal knowledge graph; storing the multimodal knowledge graph using a differentiated knowledge storage method to make different categories of knowledge interconnected; and enabling the robot to autonomously make decisions and execute tasks based on the interconnected multimodal knowledge graph. This method of classifying and storing various types of knowledge facilitates autonomous decision-making by the robot based on these types of knowledge.

The invention relates to the technical field of knowledge base construction, and discloses a knowledge base construction method for traditional Chinese medicine practitioners, and the design process of the knowledge base construction method sequentially comprises the steps of multi-dimensional data source integration, AI auxiliary knowledge classification and association, dynamic updating and personalized recommendation, interactive learning platform and privacy protection and copyright management. According to the traditional Chinese medicine practitioner-oriented knowledge base construction method, by comprehensively implementing multi-dimensional data source integration, AI-assisted knowledge classification and association, dynamic updating and personalized recommendation, an interactive learning platform and privacy protection and copyright management, efficient integration, intelligent retrieval, continuous updating and personalized learning of traditional Chinese medicine knowledge are realized; the method not only greatly improves the professional quality and clinical skills of traditional Chinese medicine practitioners, but also promotes the inheritance and innovation of traditional Chinese medicine knowledge, and injects new vitality to the development of the traditional Chinese medicine field.

Provided herein is a novel method referred to as knowledge constrained tree search decoding (KCTS), which is a first discriminator guided constrained decoding method for knowledge-based generation. The KCTS method also uses Monte Carlo Tree Search Decoding (MCTS) rather than a conventional LM decoding method that reorders the importance of tokens starting from each token using multiple simulations based on the estimated future loyalty. In combination with a novel token hierarchy hallusion detection method which is trained to predict the starting point of a hallusion token and enables a knowledge classifier defined on a sequence hierarchy to effectively adapt to the token hierarchy: Reward Inflection Point Approximation (RIPA), the novel method can greatly relieve the hallusion problem of LLM without fine tuning, and can improve the hallusion detection efficiency. Thus, high computational costs are prevented from being caused.

The present disclosure provides a question analysis method and device, electronic equipment and storage medium, relates to the technical field of Internet, and particularly relates to the field of knowledge graph. The specific implementation scheme is: obtaining a question input by a user; performing knowledge classification on the question according to a pre-constructed classification type to obtain classification information of the question; performing knowledge understanding on the question to obtain subject segment understanding information and predicate segment understanding information of the question; and generating final analysis information of the question based on the subject segment understanding information and the predicate segment understanding information and the classification information. The embodiments of the present application can provide a general analysis scheme for knowledge class Query, can be applied in different scenes with knowledge class demand, and have stronger explainability and higher accuracy.

The present invention discloses a method and system for classifying electric power label knowledge based on a large model, and relates to the field of data processing. The method includes: collecting electric power source data and determining effective source data; determining a hierarchical label map and supervising the training of an open source large model; introducing an unlabeled standard semantic library to determine the initialization classification model; reading downstream task features, performing supervised adjustments, and determining a large classification model; receiving a pre-classification task, making a classification decision, and determining a classification result; if the classification result of the pre-classification task is vacant, receiving a newly added defect type and performing class incremental learning. This method solves the technical problem in the prior art that electric power knowledge labels are highly specialized, resulting in scarce label category data and poor interpretability, and realizes the introduction of domain knowledge to enhance the interpretability of the model, achieves label classification of standard knowledge, and is used to predict and infer new sample data.

The present application relates to the technical field of computer sentiment analysis, and particularly relates to a layered noise injection based on dynamic sensitivity driven association sentiment knowledge model construction method. It comprises the following steps: downloading the model to the local client; obtaining the local client user emotion entity sensitivity classification; injecting noise into the information input in the local client; training the downloaded local client emotion knowledge classification model; updating the server emotion knowledge classification model. Through the fusion of semantic correlation, social influence weight and data sparsity and other multi-dimensional features, the present application realizes the fine sensitivity classification of different emotional data. The method effectively solves the problem that the traditional unified noise injection mechanism cannot adapt to the sensitivity difference of emotional data. Users do not need to rely on complex privacy risk assessment experience, and can configure the optimal privacy protection strategy for different types of emotional data according to the sensitivity classification results generated by the system.

The application discloses a decision auxiliary question and answer method based on subdivided industry knowledge classification and an open source large model, comprising the following steps: 1, constructing an industry knowledge classification method; 2, classifying and vectorizing and storing classified knowledge of multi-source heterogeneous data; 3, similarity matching of classified auxiliary query and knowledge; 4, combining matched industry knowledge and decision auxiliary query into prompt and inputting the prompt into multiple open source large models to obtain corresponding decision auxiliary answers. The application combines multiple methods to construct a subdivided industry knowledge classification method, can utilize more fine-grained industry knowledge to improve the effect of decision auxiliary answers of the large model, simultaneously utilizes a text quality scoring model to sort and display answers of multiple open source large models, fully gives play to respective advantages of different large models, and thus improves the rationality and accuracy of decision auxiliary answers.

The application discloses a kind of based on big model's multimodal knowledge automatic classification and retrieval method and system, it is related to knowledge classification retrieval technical field, including to knowledge fragment is classified, obtains knowledge classification data;Retrieval text is input in platform by user, the interredundancy degree between different candidate knowledge categories of retrieval text is analyzed, the retrieval fit degree of different knowledge fragments in different target knowledge categories to retrieval text is analyzed, and marked retrieval data is obtained;The retrieval quality of marked knowledge fragment in target knowledge category to retrieval text is evaluated, and target retrieval data is obtained;According to target retrieval data, the retrieval answer of retrieval text is generated, and is output to user through platform, so that last generation retrieval answer not only with the content of user's retrieval text content is fit, and also makes different modal knowledge data effectively combined, greatly improve the quality of generated retrieval answer.