75 results about "Knowledge area" patented technology

Systems and methods for dynamic knowledge integration in LLM systems including receiving multimodal input data comprising text, image, audio, video, and / or code data, extracting information by processing the multimodal input data through a document processor, storing the extracted information in a dynamic knowledge base, receiving a user query at a query processor, identifying knowledge domains related to the user query using domain-specific agents, retrieving real-time information from the dynamic knowledge base responsive to the identified knowledge domains, integrating the real-time information into the processing of an LLM by a dynamic knowledge integrator, and generating a response using the LLM with the real-time information.

The invention relates to the technical field of intelligent teaching, and discloses an intelligent teaching system and method based on a large language model. The system comprises a teaching intention analysis module, a knowledge graph adaptation module, a dynamic reasoning engine module, a teaching strategy generation module and a feedback optimization module. The teaching intention analysis module is used for disassembling the teaching interaction instruction into a knowledge domain label and a teaching behavior sequence through a semantic segmentation engine; and the knowledge graph adaptation module is used for matching the subject knowledge graph and extracting an associated knowledge node set. The dynamic reasoning engine module inputs the node set into a large language model to complete multi-hop reasoning, and an intermediate state vector containing a reasoning path is generated; and the teaching strategy generation module generates a hierarchical teaching strategy in combination with the vector path weight and the behavior sequence timestamp. The feedback optimization module collects user behavior data, updates knowledge graph matching rules through incremental learning, and adapts to diversified teaching requirements.

A scalable expert foundry system enables creation, management, and coordination of multiple specialized expert domains, each developing autonomous cognitive capabilities through geometric manifold formation while maintaining hierarchical oversight and cross-domain knowledge transfer. The system utilizes a Persistent Cognitive Machine architecture with hierarchical supervisory networks that provide multi-layered coordination, conflict resolution, and quality management across distributed expert domains. Cross-domain coordinators orchestrate communication and knowledge sharing between domains through geometric abstraction and manifold projection techniques that preserve semantic integrity while enabling beneficial knowledge propagation. Executive manifold supervisors implement second-order control architectures managing meta-cognitive capabilities and system-wide reasoning strategies. The system supports enterprise deployment across multiple geographic regions with distributed computing resources. Expert domains achieve operational readiness through statistical observables monitoring including cache hit rates, distance distribution shifts, and trajectory coherence measurements that validate manifold maturity. The architecture enables scalable expert-level performance across diverse knowledge domains while maintaining coordination effectiveness and quality standards.

Existing methods for implementing artificial intelligence (AI) models for given training data heavily depend on AI expertise, meaning that organizations need to hire experts to implement the AI model. The present invention discloses a method and process for a platform that eliminates the need to be proficient in AI and coding expertise by automating much of the process. The platform automatically evaluates and selects the best algorithms and methods for each presented problem and dynamically generates tailored AI models and workflows that meet the specific requirements of the particular training data and knowledge domains. The invention may also be configured to learn from experience and continuously improve over multiple sessions.

System and method for using knowledge fabric based on knowledge ontology, designed for deep language understanding and mechanistic causal reasoning, and meta-knowledge repository for auditable question answering. The method includes receiving an input text from a user, building a knowledge graph that represents real world facts and associations in the form of contextually tagged and weighted knowledge propositions, in multiple knowledge domains. The knowledge graph in combination with causal path knowledge and metadata describing digital sources containing answers constitutes the knowledge fabric. The method includes resolving ambiguity and determining actual intent of the user for the input text, from a plurality of interpretations of intent for sentences using the knowledge graph in conjunction with logical inference to achieve deep natural language understanding. The method includes finding / delivering response to the input request as to why / how unknown factors resulted in known outcome, or what outcomes are likely given known causal factors.

Knowledge-based audio-text modeling via automatic multimodal graph construction is performed. An audio dataset is received, the audio dataset including clips of audio data, wherein each of the clips of the audio data is paired with corresponding metadata descriptive of the audio contents of the respective clip of the audio data. Graph nodes of interest are identified from a sematic network, the graph nodes being descriptive of semantics of the knowledge domain of the contents of the audio dataset. A large language model (LLM) is utilized for categorizing the metadata into the graph nodes and for inferring supplemental data for the graph nodes for which there is no metadata, producing an extracted knowledge graph. The extracted knowledge graph is validated utilizing the LLM to perform relation verification of edges between the graph nodes of the extracted knowledge graph, thereby mitigating hallucination effects in the categorizing and inferring of the supplemental data.

Techniques disclosed herein relate generally to constructing a customized knowledge graph. In one embodiment, entities and relations among entities are extracted from a user dataset based on certain rules to generate a seed graph. Large-scale knowledge graphs are then traversed using a finite state machine to identify candidate entities and / or relations to add to the seed graph. A priority function is used to select entities and / or relations from the candidate entities and / or relations. The selected entities and / or relations are then added to the seed graph to generate the customized knowledge graph.

The invention relates to a multi-agent collaboratively-driven power marketing question and answer method and device, computer equipment, a computer readable storage medium and a computer program product, and can be applied to the technical field of artificial intelligence. The method comprises the following steps: constructing a plurality of problem sequences according to historical interaction information; performing keyword extraction on the plurality of question sequences to obtain a first keyword set and a second keyword set; labeling the first keyword set and the second keyword set to obtain a problem data set; determining a target problem sequence; constructing a portrait vector, and constructing a category labeling sequence; inputting the portrait vector and the category labeling sequence into a knowledge domain supplementary category prediction model for processing to obtain knowledge domain supplementary category information; distributing the question task of the user to the intelligent agent of the corresponding knowledge field for processing, and obtaining a plurality of pieces of reply information; and carrying out fusion processing on the multiple pieces of reply information to obtain a query result of the user. The question and answer accuracy can be improved by adopting the method.

Context-aware content filtering adapted for a knowledge domain is provided. In certain examples, a classification confidence score by a classifier indicates a level of confidence that a prompt from a user is associated with the knowledge domain. The classification confidence score is compared with a threshold. When the score is below a threshold, a violation notice is provided to the user without submitting the prompt to a generative artificial intelligence (GAI) model. When the classification confidence score is above the threshold, the prompt is further processed to determine, according to rules, whether the prompt should be submitted to the GAI model. In various examples, the rules are applied to contextual information, safety score information, and intent information derived from the prompt.

The invention provides a method for creating a knowledge base for an LLM, and the knowledge base created for the LLM comprises a knowledge graph constructed based on knowledge documents uploaded by a user. Comprising the steps of obtaining a knowledge document uploaded to a target knowledge base by a user; the user carries out user-defined modification on a first cue word template corresponding to a preset segmentation rule to obtain a first cue word corresponding to the knowledge field to which the knowledge document belongs; wherein the first prompt word is used for describing a segmentation rule customized by the user for a knowledge field to which the knowledge document belongs; sending the knowledge document and the first cue word to an LLM, so that the LLM segments the knowledge document into a plurality of document fragments based on a segmentation rule described by the first cue word; and extracting a knowledge triple from the document fragments, creating sub-knowledge maps respectively corresponding to the plurality of document fragments based on the extracted knowledge triple, and storing the sub-knowledge maps in the knowledge base.

The invention discloses an intelligent AI interactive question-answering method and system applied to science popularization and a storage medium, and the method comprises the steps: constructing a science popularization knowledge spectrogram based on multi-source science popularization knowledge; extracting key feature data based on a voice or text question input by a user, and generating a question feature vector; similarity matching is carried out on the basis of the feature vectors and a node embedding space of the science popularization knowledge spectrogram, and accurate knowledge sub-graphs related to questions are extracted; after completing the response of the current question, recording a storage positioning index of the knowledge sub-graph corresponding to the question in the popular science knowledge spectrogram, and generating knowledge sub-graph index sequence data; and based on the next question of the user, carrying out correlation analysis, including questions of the same and different knowledge types, and carrying out sub-graph matching or full-graph matching, and if a plurality of knowledge fields are involved, carrying out sub-graph matching and full-graph matching. The method has the advantages that efficient knowledge matching is realized by fusing multi-source popular science knowledge and feature extraction, user questions are quickly responded, and the matching precision is continuously optimized.

The invention belongs to the technical field of computers and text data processing, and particularly discloses a medical inquiry text information processing method and device and electronic device.The method comprises the steps that a target medical inquiry text of a target object is obtained; key terms are matched in the target medical inquiry text through term knowledge bases in different knowledge fields; based on the key terms of the target medical inquiry text in different knowledge fields, constructing a field knowledge graph of the target medical inquiry text; based on the target medical inquiry text and a domain knowledge graph of the target medical inquiry text, determining a physiological obstacle level and a psychological obstacle level of the target object through a pre-trained medical inquiry text information processing model, the disorder level is used for representing the severity of the physiological disorder or the psychological disorder. Through the technical scheme provided by the invention, the accuracy of processing the medical inquiry text information can be improved.

Systems and methods for implementing domain-specific agent networks including configuring specialized agents optimized for retrieving information from a respective specific knowledge domain, receiving a user query, analyzing the user query to identify relevant knowledge domains, activating a subset of the specialized agents corresponding to the relevant knowledge domains, retrieving information by the subset of specialized agents, aggregating the retrieved information including information from a plurality of knowledge domains, providing the aggregated information to one or more h-LLMs, receiving a plurality of responses from the one or more h-LLMs, and generating a comprehensive response from the plurality of responses, the comprehensive response incorporating information from the plurality of knowledge domains.

The invention provides an information processing method and device, electronic equipment, a storage medium and a program product. The method comprises the following steps: identifying a target knowledge field to which to-be-processed request information belongs; based on the request information, querying from a first database to obtain a plurality of analysis strategies of the target knowledge field; determining the matching degree between each analysis strategy and the request information; determining at least one target analysis strategy based on the matching degree between each analysis strategy and the request information and the plurality of analysis strategies; and generating reply information of the request information based on the request information and the target analysis strategy. Through the method and the device, the efficiency and the accuracy of replying the request information can be improved.

The invention provides a text analysis method and device, electronic equipment, a storage medium and a product. The method comprises the following steps: segmenting a to-be-processed text to obtain a plurality of text segments; clustering the word vectors in all the text segments, determining clustering centers to which the word vectors belong, and determining a first knowledge field of the word vector corresponding to each clustering center; the first knowledge field is used for indicating a knowledge category to which a word vector belongs; determining a vector difference between any two word vectors, and reserving the word vectors of which the vector differences are greater than a preset difference threshold in each text segment to obtain an updated text segment; based on the first knowledge field to which the word vector in each updated text segment belongs, determining a second knowledge field associated with each updated text segment; and determining the proportion of the word vectors in the second knowledge field in the to-be-processed text, and determining a field distribution result of the to-be-processed text according to the proportion.

The invention provides a text processing method and device, electronic equipment, a computer program product and a computer readable storage medium. The embodiment of the invention can be applied to scenes for carrying out standardization processing on non-standard texts in the fields of medicine, chemistry, geographic information systems and the like; the method comprises the steps of querying a plurality of candidate texts from a term library of a target knowledge domain based on a to-be-converted text of the target knowledge domain; generating a task prompt instruction based on a to-be-converted text and the plurality of candidate texts; obtaining a positive task example and a negative task example based on the to-be-converted text; and based on the positive task example, the negative task example and the task prompt instruction, converting the to-be-converted text to obtain a converted text including the term of the target knowledge domain. Through the method and the device, the accuracy of the converted text can be improved.

The application provides a kind of multi-modal knowledge retrieval method and system for construction image, the method comprises: obtaining construction image, and the relevant construction image is generated by data enhancement processing to construction image;Intelligent large model is used to analyze construction image to extract construction subject, knowledge field and application scene of construction image, and determine the knowledge base theme involved in construction image;The vectorization processing of relevant construction image is carried out using multi-modal coding model to generate semantic vector to be used as retrieval vector to recall matched first knowledge item set;The construction subject of construction image is used as query statement to recall matched second knowledge item set;Intelligent sorting recommendation is carried out to knowledge item in knowledge item set;Select top K knowledge item, according to the analysis content of construction image, construction image and top K knowledge item, build prompt project, and then use intelligent large model to analyze task again, finally output accurate and context-related answer.

An improved knowledge graph for augmenting queries in a retrieval augmented generation system for generative artificial intelligence is constructed using entity data comprising information regarding a first entity of a first entity type and a second entity of a second entity type, the first and second entity types being defined by a domain-specific ontology for a knowledge domain. Relationship data for the knowledge graph comprises information regarding relationships between the first and second entities using relationship definitions from the domain-specific ontology. The knowledge graph is constructed by adding nodes corresponding to the entities and edges corresponding to the relationships. In some examples, the graph is used to identify cybersecurity threats applicable to a specific context.

Systems and methods receive an access request for a knowledge domain framework for generative AI model development, the access request including user credentials, and filter, based on the user credentials being authenticated, permissions defining a user-specific access level for utilizing the knowledge domain framework. Display of a user interface that includes prompts facilitating inputs to the knowledge domain framework is initiated, the prompts being regulated based on the permissions. Information to establish a desired knowledge domain is received from a user device associated with the user interface, the desired knowledge domain including a corpus of selected documents, and an indication of a type of a generative artificial intelligence model to be developed is received from the user device. Display of a prompt template for receiving user inputs and providing generative outputs is initiated, and text submission(s) are received. Response(s) to the text submission(s) are generated.

Systems and methods receive an access request for a knowledge domain framework for generative AI model development, the access request including user credentials, and filter, based on the user credentials being authenticated, permissions defining a user-specific access level for utilizing the knowledge domain framework. Display of a user interface that includes prompts facilitating inputs to the knowledge domain framework is initiated, the prompts being regulated based on the permissions. Information to establish a desired knowledge domain is received from a user device associated with the user interface, the desired knowledge domain including a corpus of selected documents, and an indication of a type of a generative artificial intelligence model to be developed is received from the user device. Display of a prompt template for receiving user inputs and providing generative outputs is initiated, and text submission(s) are received. Response(s) to the text submission(s) are generated.

The invention discloses a simulation behavior rule automatic generation system based on knowledge graph and data fusion, a processor and a storage medium, and relates to the technical field of building energy consumption simulation and artificial intelligence. A behavior pattern mining module mines and constructs a Meta Event database from original time sequence data; the knowledge extraction module generates general knowledge through multi-stage intelligent filtering, screening and extraction; the field specialization module compiles the general knowledge into a modeling blueprint and generates specialized knowledge; the hierarchical knowledge graph construction module constructs a knowledge graph, and processes and stores general knowledge and specialized knowledge based on the hierarchical knowledge graph; and the knowledge-data offline fusion module carries out matching, calibration and entity interpretation on the behavior rules in the knowledge graph and a database to generate a fusion behavior rule base. According to the method, the literature theory, the measured data and the physical entity are systematically fused, so that the automation degree, the interpretability and the data fidelity of simulation model configuration are remarkably improved.

The invention discloses an AI-based competition teaching quality evaluation method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: carrying out the feature matching of a competition teaching video through taking the knowledge field with the least score of a student during competition as a feature, and determining whether the competition teaching video of the knowledge field with the least score exists or not; and performing secondary analysis on the competition teaching video to determine the competition teaching quality. The method comprises the following steps: firstly, determining the knowledge field with the least scores of students during competition, then, determining competition teaching contents by analyzing competition teaching videos for multiple times, and finally, comprehensively analyzing the knowledge field with the least scores of the students during competition and the competition teaching contents to determine whether the competition teaching quality reaches the standard or not. According to the method, the problem that teachers are only required to improve the competition teaching quality is solved, reasons for low scores of some knowledge points are determined, the corresponding teaching schemes are designed for the knowledge points, and rationalization of competition teaching is achieved.

The invention discloses a method for extracting entities and relationships from technical documents, which is carried out in a highly automated manner and realizes a more complete and more accurate result in a shortened time range. Several deep learning models are trained using a corpus of fields of interest tagged by experts and linguistists. A graph vector model is also trained. Manual annotation and revision are the lowest necessary conditions for obtaining an automated model that can automatically extract entities and relationships from a corpus. Once trained, these models can be used for any corpus within the same field of knowledge.

The invention discloses a method, device and system for improving RAG retrieval capability and a storage medium. The method for improving the RAG retrieval capability in the embodiment of the invention comprises the following steps: clustering each knowledge base in a multi-source knowledge base through a predetermined clustering model to obtain a clustering center corresponding to each knowledge base; performing similarity matching on the user query and the clustering center corresponding to each knowledge base, so as to select a plurality of similar knowledge bases which have higher similarity with the user query from the multi-source knowledge base; and taking the plurality of similar knowledge bases as a retrieval range corresponding to user query. In this way, by conducting clustering sensing routing in the multi-source knowledge base, efficient knowledge field positioning can be achieved, and the retrieval range can be narrowed.

This application discloses a question-answering model training method, answer generation method, device, equipment, and medium, relating to the field of natural language processing technology. The question-answering model training method includes: obtaining a structured database in the field of water conservancy knowledge, generating a first knowledge graph based on the structured database; obtaining an unstructured database in the field of water conservancy knowledge, updating the first knowledge graph based on the unstructured database to generate a second knowledge graph; training a pre-trained large language model based on the second knowledge graph, and obtaining a first question-answering model after the training is completed; obtaining a dataset of professional terminology question-answer pairs, fine-tuning the parameters of the first question-answering model based on the dataset of professional terminology question-answer pairs to obtain a second question-answering model; and the second question-answering model is used to process the obtained water conservancy knowledge questions and generate a final answer. This application can solve the problem of low accuracy of answers to questions in the water conservancy field in the existing technology.

This invention discloses a large-model-driven method and system for constructing a building knowledge graph. It generates a terminology feature library by differentially annotating unstructured building document data with semantics; based on the terminology feature library, it detects cross-document conflicts to generate a set of conflicting knowledge points; and constructs a building knowledge graph through cross-source semantic difference quantification and difference-oriented knowledge fusion using a large language model. It identifies knowledge backlog nodes and marks weak knowledge areas through topological structure analysis, and injects graph knowledge vectors in a targeted manner to generate a knowledge-enhanced control model. Based on the knowledge-enhanced control model, it executes bidirectional causal reasoning of the HVAC system to generate a decision reasoning chain, and outputs interpretable control decisions after violation of aggregation patterns identification and weight reduction processing. It generates behavioral deviation values ​​based on the comparison between equipment behavior data and the deviation of the decision reasoning chain, and triggers adaptive reconstruction of the building knowledge graph through hierarchical over-limit identification, achieving continuous accumulation of building knowledge and steady improvement in the quality of HVAC control decisions.

The invention relates to the technical field of cultural transmission, in particular to a cultural transmission system and method based on the meta universe, which comprises the combination of meta universe cultural transmission augmented reality equipment and cloud and is mainly used for connection of a terminal and a playing platform, information of a cultural transmission environment and feedback of a cultural transmission virtual image. The mMTC (Mass Machine Type Communication) provides information of the equipment and receives feedback, the eMBB (Enhanced Mobile Broadband) provides transmission of cultural transmission images (including sounds), performs classified information linking on meta-universe information, and compared with a short video area, an information knowledge area and a cultural transmission area, the information transmission efficiency is improved in the information transmission process. And skipping to a block chain node which is pointed by the link and contains the specific cultural content or propagates the content service so as to obtain the content or the service.

The application discloses a kind of based on two-stage semantic matching's distribution network engineering completion settlement data intelligent auditing method, comprising the following steps: S1 model preparation and knowledge domain dataset construction;S2 two-stage semantic matching;S3 engineering quantity data association and calculation.The method innovates and proposes the two-stage semantic matching strategy of " rough matching reduces range + accurate positioning of fine matching ": first stage carries out batch semantic matching, and quickly filters candidate entries;Second stage carries out secondary accurate matching.At the same time, further design dynamic threshold adjustment mechanism avoids wrong and missing matching, and considers matching efficiency and accuracy.Compared with artificial auditing, the method greatly shortens the auditing cycle, reduces labor cost, improves auditing efficiency and accuracy, effectively solves the accurate matching problem of semantically similar expressions, and provides an efficient, reliable and intelligent solution for distribution network engineering completion settlement auditing.Accordingly, the corresponding auditing system can be constructed to realize the automatic and intelligent matching of distribution network engineering completion settlement data.

The invention belongs to the field of false information detection, and discloses a multi-field false information detection method and system based on a fact information mode and a large language model.The method comprises the steps that firstly, false information is classified, the false information is classified into a specific field, and related information is retrieved only in the specific field to serve as evidence to be input into a recognition model; and a false information identification result is obtained. By comparing the recognition effects of an open source large model before and after the method is introduced, the multi-field false information recognition effect of the large language model can be effectively improved, the problem of unbalanced knowledge field distribution of the large language model is relieved, and the large language model can better complete a false information recognition task.