2204 results about "Text corpus" patented technology

Large language models (LLMs) are versatile in responding to user questions on a wide variety of topics. However, LLMs suffer from several drawbacks, such as hallucinations, incomplete information, and inability to cite original sources of information. Disclosed herein are systems and methods for using an LLM in a restricted manner to respond to queries regarding document corpora, e.g., documents related to a set of products, such that the impact of these drawbacks is minimized. Information retrieval is coupled with LLMs to build a question and answer (Q&A) system on the text corpora. Complex retrieved information, incorporating human feedback, and recommendations in the Q&A system are provided.

The invention provides a multi-source heterogeneous corpus fusion method and system based on government affair service data, and the method comprises the steps: obtaining an original corpus set of a plurality of data sources in government affair service, carrying out the cross-modal semantic alignment processing of each corpus unit in the original corpus set, generating a normalized data block corresponding to each corpus unit, and carrying out the fusion of the data blocks; carrying out multi-modal semantic coding on the standardized data blocks to obtain semantic feature vectors of all corpus units, carrying out topological structure coding on association attribute sets among the standardized data blocks to generate a global structure relation graph, and carrying out dynamic weight distribution on the semantic feature vectors based on node connection weights in the global structure relation graph to obtain semantic feature vectors of all corpus units; and generating a fusion weight matrix, performing cross-modal feature fusion on the semantic feature vector to obtain a target semantic embedding representation, and generating a standardized corpus associated with the government affair service. According to the method, the semantic aggregation problem of the non-uniformly distributed corpus units is solved, and the government affair data governance efficiency and the cross-department cooperation capability are greatly improved.

One or more unit-test cases are generated from a monolingual code corpus and the generated unit-test cases are filtered to generate a corpus of unit-test cases which have acceptability scores exceeding one or more predefined thresholds. One or more of the code samples of the monolingual code corpus are translated from a source language to a target language using a pretrained Large Language Model and the generated unit-test cases are translated from the source language to the target language. The LLM-translated code samples are validated using the translated unit-test cases and a parallel-data training corpus comprising the LLM-translated code samples that pass the validation is created. The pretrained large language model (LLM) is fine-tuned using the parallel-data training corpus, a given code segment is translated using the fine-tuned large language model (LLM), the translated given code segment is tested and the tested given code segment is deployed.

The invention discloses a knowledge graph construction method and system based on traditional Chinese medicine classics, and relates to the technical field of knowledge graph construction, and the method comprises the steps: collecting multi-source heterogeneous data of traditional Chinese medicine classics, carrying out the standardization processing, and generating a cross-time aligned standardized corpus through optical character recognition and multi-modal feature extraction; based on a language model and a causal reasoning engine, extracting an entity relationship and a dialectical rule from the standardized corpus, and generating a dynamic dialectical reasoning model supporting nonlinear reasoning; obtaining an output result of the dynamic dialectical reasoning model, and constructing a redundancy-removed and dynamically-calibrated traditional Chinese medicine knowledge base through knowledge fusion and conflict resolution of various traditional Chinese medicine classics; based on edge calculation and privacy protection technologies, real-time iteration and clinical curative effect feedback optimization of the knowledge graph are realized. According to the method, the problems of trans-era evolution, regional expression difference, multi-modal feature splitting and the like in the traditional Chinese medicine classics digitalization process are solved.

The invention relates to the technical field of artificial intelligence, in particular to a knowledge graph construction method and system based on a large model technology, and the method comprises the following steps: carrying out large model enhanced data annotation; performing entity extraction, relationship extraction, event extraction and causal relationship extraction by utilizing the large model; performing entity type extraction, relation type extraction, event type extraction and knowledge system extraction by utilizing the large model; the knowledge graph data is complemented by using a large model, so that the knowledge complementing capability is improved; performing relation reasoning and event reasoning by using the large model; the knowledge graph construction method and system based on the large model technology have the beneficial effects that the large model masters strong semantic understanding and context reasoning capabilities through deep learning and wide corpus training. Therefore, the knowledge graph can more accurately analyze the complex semantic relationship in the text and identify important entities and relationships hidden in the text, so that the information is effectively classified and integrated.

The invention discloses an image-text matching method based on progressive semantic aggregation and structured cognitive enhancement, and relates to the technical field of image-text matching, comprising the following steps: S1, multi-modal feature extraction; s2, introducing a hierarchical self-enhanced semantic perception pooling mechanism; s3, introducing a structured knowledge auxiliary learning module; s4, introducing a cross-modal semantic alignment mechanism; s5, introducing a multi-scale semantic association matrix; according to the method, through multi-level semantic enhancement and fine-grained level self-adaptive feature aggregation, a significant word field is enhanced, and consistency and unification between local representation and global representation are achieved; extracting structured semantics between entities from an image title corpus, mining high-order relationships in long and short sentences, and expanding concepts missed in text global embedding by utilizing the priori knowledge; a cross-modal relation interaction mechanism is introduced, semantic embedding is enhanced, and more consistent semantic understanding is promoted; a multi-scale semantic association matrix is introduced, and a more comprehensive and accurate similarity measurement matrix is generated.

The invention relates to a multisource pavement disease identification method based on a language and an image large model, and the method comprises the following steps: collecting related standards of road pavement disease detection, building a knowledge corpus, and reading a road disease image through a large language model LLM; when it is determined by the LLM that the crack crosses the whole image, cutting is carried out in the direction perpendicular to the crack by passing through the center point of the image, and the image is cut into two images; afterwards, all images and corresponding text prompts are input, target detection is carried out on pavement diseases by using a visual language large model VLM, and a prediction box is output; and performing fine adjustment on the SAM by using the image marked with the disease mask to obtain the RoadSAM adapted to the road disease segmentation task. According to the method, a large language model, a visual language large model and a segmentation large model are combined, corresponding fine adjustment is carried out on the segmentation large model SAM, dependence on a large amount of annotation data is reduced, and meanwhile unified segmentation of multi-source and multi-mode pavement disease images is achieved.

A programming system to create programs. Data are stored that describe actions of the users in creating the programs. The programming system has a library of templates for functions. A graphical user interface presents to users functions depicted as templates of blocks to be selected for incorporation into programs. Users direct the system to assemble functions from the set into the programs. The graphical user interface depicts the incorporated functions as graphical elements for manipulation in the graphical user interface. Users can graphically connect data output connection points of incorporated function graphical elements to input connection points of incorporated function graphical elements. A trained artificial intelligence large language model has been trained with a corpus of graphical programs to compute suggestions to the user for functions to be added into the program. The computation of function suggestion is based at least in part on a prompt given by the user and the trained large language model.

The invention discloses a hypergraph-based financial question and answer retrieval enhancement generation method and system, and the generation method comprises the steps: carrying out the blocking processing of a document stored in a corpus in advance, and obtaining text blocks; performing entity relationship extraction on the text blocks to obtain nodes and edges, and obtaining a node set and an edge set according to the nodes and the edges; constructing a hypergraph through a community clustering detection algorithm based on the node set and the edge set, and generating a corresponding abstract by using a large language model; constructing a knowledge graph according to the text block, the node set, the edge set, the hypergraph and the abstract; and performing node and hyperedge retrieval on the constructed knowledge graph to generate a final answer. According to the method, a retrieval enhancement generation method is used for answering complex financial questions, the illusion phenomenon of a large language model is reduced, and the answering reliability is improved; retaining a topological structure of the source text content; the hyperedge has abstract representation on the knowledge graph at different levels, and provides multi-dimensional selection for the context of the large language model.

Embodiments of the present invention provide an innovative Retrieval-Augmented Generation (RAG) system tailored for financial analysis, significantly enhancing the precision and contextual relevance of Large Language Models (LLMs). A part of the system is a query augmentation component that leverages a knowledge graph to semantically enrich user queries, ensuring comprehensive retrieval of pertinent financial documents. A noise filtering mechanism refines the search results, while a relevance ranking component prioritizes documents based on context (e.g., user and task). The system employs prompt engineering to guide the LLM in generating responses that meet the specific requirements of financial analysis. Additionally, the LLM is fine-tuned using a corpus of financial questions and answers, reinforced by human-in-the-loop feedback, to adapt the model to the financial domain's unique linguistic and structural nuances. This advanced RAG system offers financial professionals timely, reliable, and actionable insights, providing a competitive edge in a rapidly evolving financial landscape.

The invention relates to the technical field of intelligent question answering methods, in particular to a case question answering method based on a large language model, a medium and equipment. The method specifically comprises the steps of obtaining graphic and text information and related questions of a case; and inputting the intelligent question and answer model to obtain an optimal answer. The intelligent question and answer model is obtained through the following steps: training a pre-training model through a constructed multi-modal corpus based on transfer learning to obtain a base model; based on LoRA and P-Tuning, performing fine tuning on the parameters of the base model to obtain a fine-tuned large language model; introducing a CLIP module to perform feature fusion on the graphic and text information to obtain a preliminary question and answer model; introducing a thinking chain to obtain a generation model capable of outputting a plurality of candidate answers with reasoning chains; and training an existing scoring model to obtain an evaluation model capable of outputting an optimal candidate answer. According to the method, the performance of the question answering technology in the aspect of generating accurate and reliable answers can be improved, and error information or illusion is reduced.

The invention relates to the technical field of data analysis, can be applied to business scenes of medical health, financial science and technology, culture research and the like, and discloses a knowledge graph-based model analysis method, which comprises the following steps of: acquiring and processing target domain data, extracting and labeling keywords, constructing a knowledge graph comprising domain entities, a relational network and attribute characteristics, and analyzing the knowledge graph. Establishing a professional corpus and generating an analysis task, constructing a multi-dimensional analysis index system, inputting the analysis task to a to-be-analyzed model, obtaining a task output result, performing knowledge verification according to the knowledge graph, evaluating the knowledge verification result based on a multi-dimensional analysis index, and generating a final analysis result. According to the method, by fusing the knowledge graph and the multi-dimensional analysis indexes, the accuracy and comprehensiveness of evaluation are enhanced, the evaluation effect of the model in the aspects of professional knowledge understanding, reasoning ability and standard integrating degree is improved, the evaluation result is more reliable, and the application ability of the large model in the specific field is optimized.

The invention relates to the technical field of intelligent customer service, and discloses an intelligent customer service dialogue generation method and system based on user intention recognition, and the method comprises the steps: obtaining an input first user text from an intelligent customer service system, and carrying out the feature decomposition and attention fusion of the first user text, and obtaining a fusion intention feature matrix; performing intention migration analysis and dynamic Bayesian analysis on the dialogue sequence data in the historical dialogue corpus to obtain an intention state transition probability matrix; an improved Transform network model is input for joint training, and a dialogue generation model is obtained; a newly input second user text in the intelligent customer service system is decoded and generated based on the dialogue generation model, meanwhile, the intention state transition probability matrix serves as a constraint condition, a reply text conforming to the dialogue intention is obtained, the accuracy and robustness of intention recognition are improved, the reply smoothness is guaranteed, and meanwhile the user experience is improved. And the generated content is ensured to conform to an expected intention transfer rule.

The invention provides a multi-modal heterogeneous model retrieval enhancement method and system, and the method comprises the steps: building a knowledge and application example double-corpus based on user multi-modal query, and designing a joint retrieval mechanism to obtain a result set; mapping and scheduling to obtain feature representation through special processing channels for texts, images and audios and a Spiking neural network with a segmented trapezoidal topological structure; constructing a three-stage cascade architecture of a basic model, an advanced model and human experts, and obtaining a decision path and answer candidate set in combination with a recursive and discarding decision mechanism; a Hamiltonian graph network is used for representing a multi-modal relation, and a gradient-free descent method is used for rapidly training and optimizing model parameters; an enhanced retrieval result is obtained through cross-modal semantic alignment and dynamic retrieval window adjustment; and high-quality response is obtained through context-aware sorting and retrieval enhanced reasoning. According to the method, the multi-modal information retrieval processing efficiency and the heterogeneous model reasoning response quality are improved.

Apparatus and methods are disclosed for implementing a copilot as a network of microservices including specialized large language models (LLMs) or other trained machine learning (ML) tools. This architecture supports flexible, customizable, or dynamically determinable dataflow. Compared to much larger competing LLMs, comparable or superior performance is achieved for certain tasks, while significantly reducing computation time and hardware requirements, even to a single compute node with a single GPU. An expansion microservice converts client input tokens into associated tokens to diversify targeted tasks presented to a core microservice. An ML tool in the expansion microservice is pretrained in multiple stages for varying tasks using varying general and target-specific corpora. Synthesized training data derived from a knowledge graph can also be used. The expansion ML tool is subsequently fine-tuned in one or multiple stages. Variations and additional techniques are disclosed.

A computer-implemented method for operating an artificial intelligence voice agent system includes receiving voice input through communication channels; analyzing converted text through natural language processing (NLP) pipelines implementing intent recognition and sentiment analysis detecting emotional cues using a multimodal large language model (LLM); generating response content using machine learning models trained on domain-specific corpora; converting generated responses to synthetic speech through text-to-speech (TTS) engines; integrating with a customer relationship management (CRM) platforms or an enterprise resource planning (ERP) database; and implementing continuous learning by updating language understanding models using conversation logs, voice recognition parameters based on user feedback, and response generation patterns. One implementation is a computer-implemented system and method that operates a suite of intelligent interactive devices and platforms including an artificial intelligence voice agent, enhanced communication platforms, an intimacy companion system, and augmented / virtual reality eyeglasses. Further, one implementation includes AR / VR eyeglasses that project visual content onto interchangeable lenses or directly onto the user's retina via laser-based retinal projection, provide prescription adjustments, incorporate ear-mounted sensors for monitoring physiological parameters like heart rate, oxygen saturation, and blood pressure, and utilize wireless data transmission, onboard environmental sensing, and remote calibration, all designed to offer dynamically adaptive, secure, and context-aware interactions across communication, personal assistance, health monitoring, and immersive augmented or virtual reality environments.

The invention provides a traditional Chinese medicine knowledge question-answering system based on a fine-tuning large model and dual retrieval enhancement. The traditional Chinese medicine knowledge question-answering system comprises a large model fine-tuning module, a dual retrieval enhancement module, a prompt template module and an answer generation module. The large model fine tuning module constructs a high-quality corpus by using traditional Chinese medicine ancient books, clinical cases and the like, performs incremental pre-training and supervised fine tuning on a ChatGLM3-6B pre-training model, and adopts technologies such as low-rank adaptation (LoRA) and direct preference optimization (DPO) to improve the adaptability of the model to traditional Chinese medicine professional knowledge. The dual retrieval module enables the model to map user questions to related contents in traditional Chinese medicine classical literatures, guidelines and modern literatures through text retrieval based on a LangChain framework on one hand, and provides structured background knowledge through map retrieval on the other hand. The system effectively makes up for the knowledge blind area of a large-scale general model in the field of traditional Chinese medicine, realizes the improvement of the accuracy, continuity and speciality of question and answer results, and has wide application prospects and relatively high innovativeness.

The invention discloses a milk industry knowledge question-answering method and device based on a large model and RAG and a medium, and the method comprises the steps: collecting multi-source heterogeneous data of the milk industry, carrying out the term protection word segmentation processing of the multi-source heterogeneous data, and generating a labeled field corpus; based on a pre-training language model base, through a domain corpus injection and adversarial learning mechanism in a domain corpus, generating an enhanced language model adapted to the dairy industry terminology; receiving a milk industry problem of a user, executing semantic vector retrieval and term extension retrieval in parallel, and screening a multi-modal retrieval result through a dynamic sorting algorithm; and splicing the multi-modal retrieval result and the milk industry question into an enhanced prompt, inputting the enhanced prompt into an enhanced language model, generating a final answer corresponding to the milk industry question, and associating the final answer with a knowledge source.

The technology provides rewriting suggestions for communication styles in different pre-defined styles. Rewriting may convert text in different ways, including visually enhancing the message. A method provides input to a trained large language model, the input including curated examples associated with one or more writing style choices. The set of curated examples has a first size. The method also includes generating, using the model, a rewriting corpus according to one or more writing style choices. The rewriting corpus has a size two or more orders of magnitude larger than a size of curated examples. The writing style choices include at least one of tone, conversion, application context, or conversation type. A text rewriting model is trained using at least a subset of the rewriting corpus. The model is configured to generate vivid textual information in response to user input in an interactive domain, according to specific writing style choices.

Methods, systems, and computer program products for collaboration systems. A method for identifying selected portions of a set of content objects for use in generating a large language model (LLM) prompt comprises: identifying a content management system (CMS) wherein collaboration activities occur over time and over content objects maintained in the CMS, and wherein the CMS maintains a historical record of occurrences of the collaborator activities over the content objects. Upon receiving a natural language query from a CMS collaborator, reducing a larger corpus of content objects to a smaller corpus of context passages that are used in an LLM prompt. The smaller corpus of passages is formed using a two-phase reduction scheme whereby firstly, selected constituents from the larger corpus of content objects are identified based on CMS metadata; and then, rather than considering the larger corpus, instead considering only the selected constituents when generating the LLM prompt.

A data processing system implements receiving, via a user interface of a client device, a query to a large language model (LLM) working in conjunction with an embedding model comprising a corpus of artifacts. The system further implements converting the query into a query embedding, transforming the query embedding into a transformed query embedding using a first transformation function that adds a first residual term to the query embedding, the first residual term being specific for a task associated with the query, measuring a first similarity between the transformed query embedding and corpus element embeddings in an embedding space of the embedding model, determining first top-rated corpus element(s) associated with the corpus element embeddings based on the first similarity, incorporating the first top-rated corpus element(s) into the query as a prompt to the LLM to generate a response to the query, and providing, via the user interface, the response.

Provided in the present invention are a method for training a natural language processing model, and a method for generating subsequent text of a dialogue. The method for training a natural language processing model comprises: acquiring multiple types of heterogeneous sample data and a pre-constructed natural language processing model, wherein the heterogeneous sample data includes structured data, unstructured data, a knowledge graph and expert experience data; performing data encoding fusion on the structured data, the unstructured data and the knowledge graph, so as to obtain encoding fused data; and on the basis of the encoding fused data and the expert experience data, training the pre-constructed natural language processing model, so as to obtain a trained natural language processing model. The present invention enables a knowledge graph to be placed in a model, not as an independent retrieval corpus, but as a method for knowledge enhancement, thereby improving the efficiency of a natural language processing model.

A computer-implemented method of training a machine learning model to identify biological entities for drug discovery is disclosed. The method comprises providing a training data set comprising a plurality of entity-linked text sequences, each text sequence including a mention of a biological entity, where the biological entity is linked to a corresponding biological entity identifier from a set of possible biological entity identifiers; masking the mention of the biological entity within each text sequence; encoding each masked text sequence into an input representation for a machine learning model; and training a machine learning model to predict the unique entity identifier of the masked biological entity based on the input representation. The described method is able to utilise the full breadth of the rich contextual information available in the biomedical text corpus to predict new biological targets for drug discovery and avoids the restrictions intrinsic to relationship prediction using knowledge graphs. The ability to identify more promising, biologically relevant targets in an automated manner, significantly reduces the requirement of human input and reduces the failure rate in targets that are progressed in the drug delivery pipeline.

The invention discloses a knowledge graph-based nursing corpus automatic creation method, and relates to the field of artificial intelligence technology and medical information processing, and the method comprises a multi-dimensional data acquisition stage, a knowledge graph construction stage, a corpus automatic generation and updating stage, and a corpus quality control and evaluation stage. According to the automatic corpus generation method driven by the knowledge graph, dynamic generation and real-time updating of corpora are achieved by constructing an ontology structure, a corpus generation template and an updating algorithm in the nursing field; through a deep learning model and a transfer learning technology, new nursing knowledge and a diversified information structure are continuously introduced into the corpus, and the diversity of corpus content is increased.

The present disclosure leverages self-supervised learning to generate positive and negative question-context pairs, enabling the model to learn robust representations. This process involves data augmentation techniques to create variations of the original questions and contexts while preserving semantic relevance. A large corpus of unlabelled text data containing questions and their corresponding contexts, ensuring diversity and representativeness across various topics are used to train a self-supervised Large Language retrieval model.

The invention provides a multimodal reasoning method based on a Monte Carlo tree and dynamic retrieval. The method is applied to an artificial intelligence assistant-assisted teacher paper judgment scene. Specifically, the framework comprises a unified retrieval module, wherein the retrieval module comprises a mixed modal retrieval corpus and a multi-modal retrieval module; the multi-modal retrieval module comprises two retrieval modules, namely a text retrieval module and a cross-modal retrieval module, key problem solving insights are selected by adopting knowledge concept filtering, and progressive multi-modal reasoning annotations of multi-modal reasoning are automatically obtained by utilizing Monte Carlo tree search and an active retrieval mechanism for data annotation; and gradually aligning a process reward model through course process reward modeling in two stages by utilizing the annotation data so as to realize fine-grained verification of multi-modal large model reasoning. An MCTS algorithm and an active retrieval strategy are combined to improve multi-modal reasoning. The framework can automatically obtain high-quality step-by-step reasoning annotations, so that a process reward model is aligned step by step, and finally reliable automatic multi-modal reasoning verification is realized.

Systems, computer program products, and methods are described herein for generating, extracting, classifying, and formatting object metadata using natural language processing in an electronic network. The present disclosure is configured to identify at least one input source, comprising at least one input data; parse the at least one input data; output, by an extraction layer, at least one product metadata and a term importance score associated with the input data to a metadata storage, the extraction layer comprising an NLP attribute extraction model; assemble, by an assignment layer, a corpus of text data and key phrases based on the product metadata from the extraction layer, the assignment layer comprising an NLP classification model; classify and verify, by the assignment layer, the product metadata; and output, by a generative layer, at least one generative metadata to the metadata storage, the generative layer comprising a pretrained generative NLP model.

The invention relates to the technical field of port vertical large model systems, in particular to a port vertical large model system based on a general large language model and a construction method. Comprising the following modules: a data acquisition module, a pre-training corpus construction module, an incremental pre-training module, a fine adjustment module, a port adaptation and optimization module, a knowledge base management module, a reasoning and man-machine interaction module and a system monitoring and optimization module. The port vertical large model has the beneficial effects that the port vertical large model can dynamically adapt to emergencies in port operation through incremental pre-training, a fine tuning technology and a real-time knowledge base updating mechanism, and multi-source data is integrated and analyzed to form a whole-process business simulation and optimization scheme. The modularized knowledge management mechanism enables the port management system to have a real-time decision support function, and improves the overall efficiency and safety of the port in the aspects of equipment maintenance, cargo scheduling, environment monitoring and the like.

A computer-implemented method for searching electronic documents is provided. The method executing a non-semantic search, such as lexical search, to identify documents from a document corpus that meet the search criteria of the non-semantic search. A subsequent semantic search can be scoped based on the results of the non-semantic search. The method can thus include executing a semantic search scoped to the documents identified in the non-semantic search result to generate a semantic search result that identifies content that is semantically relevant to a natural language query. Thus, the semantically relevant content can have both non-semantic (e.g., lexical) and semantic relevance.