Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

1461 results about "IntraText" patented technology

IntraText is a digital library that offers an interface while meeting formal requirements. Texts are displayed in a hypertextual way, based on a Tablet PC interface. By linking words in the text, it provides Concordances, word lists, statistics and links to cited works. Most content is available under a Creative Commons license It also offers publishing services that enable similar advantages.

Method and System for Optimizing Use of Retrieval Augmented Generation Pipelines in Generative Artificial Intelligence Applications

A method of generating outputs in LLMs including receiving including textual content, defining a context for the documents including identifying a topic or a category, segmenting the textual content into content chunks associated with the topic or category, assigning a tag to each content chunk, identifying selected chunks, adding metadata to the selected chunks indexing the selected chunks, receiving a query, and performing a response generation process including determining if a cache includes information for the query and either retrieving the information from the cache or performing a search of the index to retrieve the information, generating an augmented query by augmenting the query with retrieved information, generating a response from the augmented query, evaluating the response for compliance with criteria, and one of generating a final response and transmitting the final response to the user or performing a fine-tuning process comprising redefining the of the one or more contexts.
Owner:MADISETTI VIJAY

Generating adaptive textual explanations of output predicted by trained artificial-intelligence processes

The disclosed embodiments include computer-implemented processes that generate adaptive textual explanations of output using trained artificial intelligence processes. For example, an apparatus may generate an input dataset based on elements of first interaction data associated with a first temporal interval, and based on an application of a trained artificial intelligence process to the input dataset, generate output data representative of a predicted likelihood of an occurrence of an event during a second temporal interval. Further, and based on an application of a trained explainability process to the input dataset, the apparatus may generate an element of textual content that characterizes an outcome associated with the predicted likelihood of the occurrence of the event, where the element of textual content is associated with a feature value of the input dataset. The apparatus may also transmit a portion of the output data and the element of textual content to a computing system.
Owner:THE TORONTO DOMINION BANK

Generating adaptive textual explanations of output predicted by trained artificial-intelligence processes

The disclosed embodiments include computer-implemented processes that generate adaptive textual explanations of output using trained artificial intelligence processes. For example, an apparatus may generate an input dataset based on elements of first interaction data associated with a first temporal interval, and based on an application of a trained artificial intelligence process to the input dataset, generate output data representative of a predicted likelihood of an occurrence of an event during a second temporal interval. Further, and based on an application of a trained explainability process to the input dataset, the apparatus may generate an element of textual content that characterizes an outcome associated with the predicted likelihood of the occurrence of the event, where the element of textual content is associated with a feature value of the input dataset. The apparatus may also transmit a portion of the output data and the element of textual content to a computing system.
Owner:THE TORONTO DOMINION BANK

Hybrid enhanced indexing method and system based on vector retrieval and BM25 algorithm

The invention discloses a hybrid enhanced index and system based on vector retrieval and a BM2 algorithm, and the method comprises the steps: uploading a document by a user, analyzing the document by the system to obtain text content, segmenting the text content, converting the segmented text content into dense vectors, storing the dense vectors in a vector library, extracting keywords of segmented texts by using a large model, processing the keywords, and inserting the keywords into a word list. Word segmentation is carried out on the text based on the constructed word list and a word segmentation device; in response to the received user query, vectorizing the user query, and calculating the similarity with each vector in the vector library to obtain a preliminary query result; performing word segmentation on user query, performing keyword retrieval by using a BM25 algorithm according to a word list and a word segmentation device to obtain query results, and filtering the similarity of the two query results by the reordering model according to a set threshold value; selecting a result with the highest similarity according to large model parameter limitation and an upper limit set by business requirements; and splicing the document content corresponding to the result and the user query into a cue word, inputting the cue word into the large model, and analyzing a semantic relationship and a logic structure in the cue word to generate an answer.
Owner:XIAMEN MEIYABAIKE INFORMATION SECURITY RES INST CO LTD

Generation of security awareness training samples with large language models

A computer-implemented method of generating security awareness training samples may include receiving, structuring and storing information about a user of an organization into an organization knowledge base and selecting and fetching at least one training template, each including an electronic message template and a prompt template for a large language model. The prompt template(s) and the electronic message template(s) may then be specialized using the information about users of the organization stored in the organization knowledge base. The specialized prompt template(s) may then be submitted to a large language model artificial intelligence system. Textual content may then be received from the large language model responsive to each submitted specialized prompt template. A security awareness training sample may then be generated for each submitted specialized prompt template using the corresponding generated textual content received from the large language model and the corresponding specialized electronic message template(s).
Owner:VADE USA INC

Knowledge graph open domain construction and RAG question and answer method and device and storage medium

The invention provides a knowledge graph open domain construction and RAG question and answer method and device and a storage medium. The method comprises the steps of obtaining text content in a text file; performing text division on the text content to obtain text blocks; performing open domain information extraction on each text block by utilizing a large language model to obtain an initial triple; performing post-processing on the initial triad to obtain a post-processing triad for constructing the knowledge graph; constructing a knowledge graph according to the post-processing triple; the method for realizing RAG question answering based on the knowledge graph comprises the following steps: performing knowledge graph retrieval on a question to obtain a context related to the question, then constructing a question answering cue word by using the context and the question, and sorting out an answer to the question by a large language model based on the question answering cue word. According to the method, the problem that a complete knowledge graph cannot be obtained during defined domain knowledge graph construction in the face of diversified entities and relation types is solved, and the problems that RAG retrieval information is weak in correlation with problems and the multi-hop reasoning capability is limited are solved.
Owner:SHANDONG ZHIYANG SHANGSHUI INFORMATION TECH CO LTD

Document knowledge question-answering method, document knowledge storage method and document knowledge question-answering device

The invention provides a document knowledge questioning and answering method, a document knowledge storage method and a document knowledge questioning and answering device, and relates to the technical field of intelligent questioning and answering. All layers of nodes of a knowledge tree are traversed according to a target retrieval mode on the basis of the query statement to obtain a query result, the knowledge tree comprises multiple layers of nodes, the multiple layers of nodes at least comprise first-layer nodes, second-layer nodes and third-layer nodes, semantics of the first-layer nodes are semantics of text contents of knowledge point levels in the document, and semantics of the third-layer nodes are semantics of text contents of knowledge point levels in the document; the semantics of the second-layer nodes are the semantics of the paragraph-level text content in the document, and the semantics of the third-layer nodes are the semantics of the full-text-level text content in the document; and outputting an answer text corresponding to the query statement based on the query result. The method provided by the invention not only improves the recall rate of knowledge and the correlation of answers, but also enhances the overall experience of the user, so that the user can obtain more comprehensive and accurate answers in complex queries.
Owner:CHENGDU CELIS TECH CO LTD

Visual Citations for Information Provided in Response to Multimodal Queries

A result image is retrieved based on a similarity between a query image and the result image. A first unit of text is obtained, wherein the first unit of text comprises at least a portion of textual content of a source document that includes the result image. A second unit of text is determined responsive to a prompt associated with the query image, wherein the second unit of text comprises one or more of (a) at least some of the first unit of text, or (b) text derived from the first unit of text. The second unit of text and the result image are provided for display within an interface.
Owner:GOOGLE LLC

Biding document multi-mode duplicate checking method and system based on large model

The invention belongs to the technical field of natural language processing and information retrieval. The invention provides a bidding document multi-modal duplicate checking method and system based on a large model, and the method comprises the steps: carrying out the structural analysis and multi-modal feature extraction of an input bidding document, and generating the feature representation of semantic blocks and non-text elements; performing deep semantic coding on text blocks by using a dynamic context-aware large language model, and retaining logic relevance of a long text in combination with hierarchical position coding; efficient matching of massive semantic vectors is achieved through a mixed retrieval framework, and calculation efficiency is optimized in combination with a distributed calculation framework and a hardware acceleration instruction; and finally, performing structured feature reconstruction on non-text contents such as tables, charts and the like to realize cross-modal semantic association analysis.
Owner:INSPUR GENERSOFT CO LTD

Textual dataset augmentation using large language models

A system and a method for augmenting a dataset comprising a textual content using instruction to cause a conversational language model to create variations of text items by changing text properties such as length, style, terminology, dialect, rhyming and the like. The method may also be used with combined prompts and iteratively.
Owner:NEC CORPOATION OF AMERICA

Retrieval-augmented content generation for legal research

Embodiments support systems and methods for large language model (LLM)-assisted research tools that support retrieval-augmented content generation. In an aspect, the disclosed systems and methods may provide functionality for receiving, by one or more processors, a set of search criteria via a graphical user interface. The systems and methods may also include functionality for providing, by the one or more processors, the set of search criteria or information derived from the set of search criteria as one or more prompts to one or more LLMs, and for generating, by the one or more LLMs, textual content based on the one or more prompts. The textual content may include information associated with one or more legal issues associated with the set of search criteria.
Owner:THOMSON REUTERS ENTERPRISE CENTRE GMBH

Method and electronic device for generating article content

A method and an electronic device for generating article content are disclosed. The method includes: constructing a subject keyword library by collecting industry trend data, and collecting content materials for article generation; in response to a request for generating an industry information article, determining a target subject keyword and a prompt word text for dialogue with an artificial intelligence AI large language model, to facilitate a generation of an article subject; screening multiple segments of target content materials from the content materials; constructing a prompt word text for dialogue with the AI large language model according to the article subject and the target content materials to generate an article outline, the article outline including multiple sub-subjects; and calling the AI large language model multiple times to generate corresponding text contents for the multiple sub-subjects respectively.
Owner:HANGZHOU ALIBABA INT INTERNET IND CO LTD

Tag system construction method based on large language model

The invention provides a tag system construction method based on a large language model, which comprises the following steps of: 1, sorting and storing a to-be-processed text, and 2, calling a pre-trained large model to use the generation capability of the pre-trained large model to print tags; step 3, performing label post-processing on all the labels obtained in the step 2; 4, clustering the labels obtained through label post-processing in the step 3; 5, obtaining a label system by using a pre-training large model according to a clustering result obtained in the step 4; sixthly, the label system is put in storage; 7, labeling the text library obtained in the first step by using the constructed label system; according to the method, the latest progress of deep learning, natural language processing and a large-scale pre-training model is combined, the problems that a label system needs to be established in advance in current text classification and the label system cannot completely reflect text content classification are solved, the method is suitable for various text types, and the defects in the prior art are overcome.
Owner:BEIJING COMPUTING CENT

Content generation method and device

The embodiment of the invention provides a content generation method and device, and the method comprises the steps: extracting the features of text content inputted by a user, and obtaining a first feature; determining a target index matched with the first feature from an index of a preset database, wherein the index is obtained based on a second feature of the text in the preset database in advance; obtaining a text similar to the text content from a preset database based on the target index to form a reference text sample; generating prompt information by utilizing the text content and the reference text sample, wherein the prompt information is used for indicating a text generation model to generate a target text according to the reference text sample based on the text content; and inputting the prompt information into a text generation model, so that the text generation model generates a target text corresponding to the text content based on the indication of the prompt information. In this way, the relevancy between the generated target text and the text content input by the user can be guaranteed, the user requirement is better met, and therefore the user experience is improved.
Owner:INFLY TECH (SHANGHAI) CO LTD

Generating multi-modal response(s) through utilization of large language model(s) and other generative model(s)

Implementations relate to generating multi-modal response(s) through utilization of large language model(s) (LLM(s)) and other generative model(s). Processor(s) of a system can: receive natural language (NL) based input, generate a multi-modal response that is responsive to the NL based output, and cause the multi-modal response to be rendered. In some implementations, and in generating the multi-modal response, the processor(s) can process, using a LLM, LLM input to generate LLM output, and determine, based on the LLM output, textual content and generative multimedia content for inclusion in the multi-modal response. In some implementations, the generative multimedia content can be generated by another generative model (e.g., an image generator, a video generator, an audio generator, etc.) based on generative multimedia content prompt(s) included in the LLM output and that is indicative of the generative multimedia content. In various implementations, the generative multimedia content can be interleaved between segments of the textual content.
Owner:GOOGLE LLC

Text content generation method based on artificial intelligence

The invention relates to the technical field of artificial intelligence and natural language processing, and particularly discloses a text content generation method based on artificial intelligence, and the method comprises the steps: obtaining natural language text input, and extracting a semantic recognition feature vector; acquiring context state data and encoding the context state data into a state recognition feature vector; generating a fusion feature vector containing a semantic and state association relationship through fusion analysis; constructing a causal discrimination model based on the fusion features, and outputting the matching confidence of semantics and states; dynamically adjusting a generation strategy according to the confidence coefficient, if the matching degree is high, generating a standard text, otherwise, triggering an error correction mechanism to output a corrected text; and finally, performing logic consistency verification on the generated text to ensure that physical constraints, technological procedures and safety standards in the industrial field are met. According to the method, by introducing multi-level feature fusion, causal reasoning, intelligent error correction and rule verification mechanisms, context perception and safety controllability in the text generation process are achieved.
Owner:JINING POLYTECHNIC

Safety traceability knowledge graph construction method based on large language model

The invention provides a security traceability knowledge graph construction method based on a large language model, which comprises the following steps of: 1, collecting related security data, and analyzing text content; step 2, generating a data set for fine adjustment of the model by using the open general large model; step 3, performing instruction fine tuning on the local large language model based on LoRA, and analyzing the collected textualized security data by using the trained model; and 4, according to the extracted information, carrying out fusion on the entity and the relationship, and constructing a security traceability knowledge graph. The invention provides a security traceability mapping knowledge domain construction method based on a large language model, which can automatically extract entities and relationships in security data, improve the recognition accuracy of the model and more effectively construct a security traceability mapping knowledge domain.
Owner:YANCHENG POWER SUPPLY CO STATE GRID JIANGSU ELECTRIC POWER CO

Real-time artificial intelligence powered dynamic selection of template sections for adaptive content creation

A data processing system implements and iterative process for dynamically creating a template including receiving a request for a template suggestion for an electronic content item for an application on a client device. The request includes an identifier of the application and textual content from the first electronic content item. The system further implements providing the identifier of the first application and the textual content to a language model to obtain a template suggestion, the language model being trained to analyze the identifier of the application and the textual content and to output the template suggestion, the template suggestion comprising a template identifier and a first subsection identifier identifying a first subsection of the first template predicted to be relevant to the user for creating the electronic content item, sending the template suggestion to the client device, and causing the client device to present the template suggestion in the application.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Visual Citations for Information Provided in Response to Multimodal Queries

Result images are retrieved based on a similarity to a query image. A set of textual inputs is processed with a machine-learned language model to obtain a language output comprising textual content, wherein the set of textual inputs comprises textual content from source documents that include the result images, and a prompt associated with the query image. The language output and the result images are provided to a user computing device. Information is received descriptive of an indication by a user that a first result image is visually dissimilar to the query image. Textual content associated with the source document that includes the first result image from the set of textual inputs is removed. The set of textual inputs is processed with the machine-learned language model to obtain a refined language output. The refined language output is provided to the user computing device.
Owner:GOOGLE LLC

Text knowledge automatic extraction and mapping method and system based on deep learning

The invention discloses a text knowledge automatic extraction and mapping method based on deep learning, which optimizes a semantic understanding algorithm by combining a deep learning model, enhances the perception ability of the model for the internal structure and external relationship of a text, realizes comprehensive extraction and detailed relationship analysis of equipment fault knowledge, and utilizes a knowledge mapping technology to realize automatic extraction and mapping of equipment fault knowledge. According to the method, an automatic graph construction process is implemented to improve the query efficiency and analysis capability of the graph, and the method comprises the following steps: S1, performing structured processing on an original document, segmenting the original document into independent case units, and extracting key information related to an equipment fault; s2, key entities in the document and mutual relations of the key entities are recognized and marked; and S3, based on the extracted entities and relationships, constructing and updating a knowledge graph of the fault case. The system has high automation, intellectualization, expandability and modular design, can be easily integrated into an existing industrial informatization system, and assists an enterprise in realizing intellectualized transformation and upgrading.
Owner:POWERCHINA HUADONG ENG CORP LTD +1

Document processing method and system based on text content extraction

The invention relates to a document processing method and system based on text content extraction. The method comprises the steps that an original document containing text, image and format information is received, the encoding format of the document is automatically detected, character set conversion is executed, and hierarchical indexes including page numbers, paragraphs and tables are established for an unstructured document; the method comprises the following steps: synchronously processing text content and visual layout through a pre-trained visual-language model, extracting word-level and sentence-level semantic features by a text stream embedding layer, analyzing spatial distribution features of document elements by a visual encoder, and fusing text and visual features through a cross-modal attention mechanism; and loading the domain knowledge graph matched with the document type, and executing entity linking to associate the text mentions to the knowledge nodes. According to the document processing method and system based on text content extraction, through the synergistic effect of vision-text joint coding and knowledge enhancement, the accuracy of financial contract key clause recognition tasks is improved, the error rate is lower than that of industry benchmark products, and the semantic understanding precision is remarkably improved.
Owner:WIN THE BID HUIKANG TECH CO LTD

Text generation system and method based on multi-agent cooperation mechanism MOPAR

The invention provides a text generation system and method based on a multi-agent cooperation mechanism MOPAR, and the system comprises a matching agent which is connected with a field multi-agent system, and is used for obtaining the writing demands of a user, generating a matching prompt word according to the writing demands, and transmitting the matching prompt word to the field multi-agent system, performing field matching with the field multi-agent system through the matching prompt word, and performing optimization according to feedback information of an reflection agent in the field multi-agent system; and the field multi-agent system comprises a plurality of multi-agents in different fields, is connected with the matched agent and is used for receiving the matched cue word, acquiring the multi-agent in the corresponding field according to the matched cue word and generating text content required by a user through the multi-agent in the corresponding field on the basis of a multi-agent coordination mechanism MOPAR. According to the method, a cooperation mechanism among multiple agents is introduced, so that a more efficient, professional and creative text generation service is provided for the user.
Owner:数字郑州科技有限公司

Multi-literature intelligent classification and automatic review generation method based on large language model

The invention discloses a multi-literature intelligent classification and automatic review generation method based on a large language model, which is characterized by comprising the following steps of: retrieving literatures or uploading local literatures, and extracting text contents; identifying keywords by utilizing an algorithm or a large language model; converting the keyword into a vector form by using a vectorization model; summarizing the research direction of the clustering result by using a large language model; comprehensively summarizing the single literature and literatures in different research directions by using a large language model; and executing the steps of reviewing, quotation insertion and the like through a large language model and a vectorization semantic matching technology. Compared with the prior art, the method has the advantages that the efficiency and quality of document classification and review generation are remarkably improved, technologies such as text vectorization, topic clustering and large language model generation are well fused, efficient and accurate multi-document review automatic generation is achieved, the method is suitable for interdisciplinary academic document analysis and information integration application, and the method is suitable for popularization and application. Wide application potential is shown.
Owner:EAST CHINA NORMAL UNIV

Text information structured recovery method and system based on large language model and application

The invention provides a text information structured recovery method and system based on a large language model and application. The text information structured recovery method comprises the following steps: S1, extracting original text content from a webpage or an unstructured document; s2, designing a cue word template according to different scenes and target structures, and generating cue words; s3, guiding a large language model to analyze the original text content and the cue word in the step S2, and generating a text result with a hierarchical structure; s4, analyzing a text result in the step S3, constructing a semantic structure tree, and forming a multi-layer nested structure; and S5, applying the multi-layer nested structure in the step S4 to database modeling and content indexing, compared with the defects of non-uniform structure loss, poor universality and semantic understanding intelligence deficiency in the prior art, the manual processing cost can be remarkably reduced, the data structuring efficiency and accuracy are improved, and the semantic understanding intellectuality is improved. And a stable and high-quality structured text support is provided for a large model ecological system.
Owner:SHENZHEN NAT HEALTH CULTURE COMM CO LTD

Large model text auditing optimization method based on clustering preprocessing

The invention discloses a large model text auditing optimization method based on clustering preprocessing, which relates to the technical field of natural language processing, and comprises the following steps: S1, preprocessing input original text data, including text cleaning, word segmentation, stop word and punctuation mark removal and standardized text vector generation, during preprocessing, a TF-IDF algorithm is adopted to calculate a text feature weight, and a high-dimensional feature vector matrix is generated. According to the large model text auditing optimization method provided by the invention, the text is divided into clusters with similar semantics or theme contents through clustering preprocessing, and a special auditing model is constructed for each cluster, so that the models can more accurately understand the text contents, the auditing accuracy is improved, and meanwhile, the auditing efficiency is improved. Due to the fact that the data size needing to be processed is reduced through clustering, the calculation efficiency of the model is remarkably improved, the clustering center vector and the cluster division rule are continuously adjusted, and closed-loop optimization of the model is achieved.
Owner:BEIJING INFORMATION TECH BOTE INTELLIGENT TECH CO LTD

Multi-modal consistency verification and harmonization models

A system may access content comprising text content, visual content, and / or audio content. The system may perform, based on a harmonization model and / or consistency model, a harmonization check and / or a consistency check on the content. The system may recognize, based on the harmonization check and / or the consistency check, a conflict to be corrected. The system may identify a property of the content that should be changed based on the recognized conflict. The system may generate a corrective action based on the property of the content that should be changed.
Owner:REVE AI INC

Method, system and device for improving retrieval performance of RAG knowledge base and medium

The invention provides a retrieval performance improvement method, system and device of an RAG knowledge base and a medium, and the method comprises the steps: obtaining a knowledge document, extracting text information in the knowledge document, and preprocessing the text information; splitting the text information into text blocks by utilizing a large language model framework according to the text hierarchical structure; performing vectorization processing on the split text blocks by using a Chinese vector large model, and generating a semantic similarity matrix of the text blocks; combining the text blocks according to the semantic similarity matrix of the text blocks to generate combined text blocks; and storing the combined text block information into a vector database. According to the method, fine text contents are merged according to semantics from the text to the vector database storage, so that the retrieval performance of the RAG knowledge base is effectively improved.
Owner:山东浪潮智水数字科技有限公司 +1

Automatic video editing method based on semantic analysis

The invention relates to an automatic video editing method based on semantic analysis, and belongs to the technical field of video editing. The method comprises the following steps: extracting anchor point information of text content in a streaming media file based on a knowledge graph, establishing a support relationship, and determining a main anchor point, a sub anchor point and a argument anchor point by combining the support relationship and the anchor point information; constructing a dynamic trigger mechanism, setting a verification direction of the dynamic trigger mechanism, determining a semantic extension direction of the anchor point information according to the verification direction, and verifying whether a precondition chain supporting the anchor point information exists or not; and setting a credibility scoring strategy, determining the credibility of the anchor point information according to the logic complexity, the language confidence and the text consistency, forming a sequence set of the anchor point information, and splicing to form a logically coherent video editing text result. According to the method, automatic and intelligent editing of the video is realized based on semantic analysis, and the editing efficiency and quality are remarkably improved.
Owner:BEIJING GONGXIN INTERNET TECHNOLOGY CO LTD

Automated transformation of information from images to textual representations, and applications therefor

Recent developments in machine learning (commonly coined "artificial intelligence" or "AI") have vastly expanded applications for this technology, such as myriad "chat" agents adept at understanding natural human language. While state of the art generative models can parse text queries from a user and provide comprehensive, accurate responses (including generating images depicting desired content), current implementations struggle with understanding all information present in images of documents, especially images of business documents. In particular, generative models fail to understand structured and semi-structured information, e.g., as indicated by graphical information such as lines, geometric relationships (e.g., indicated by tables, graphs, figures, etc.), formatting, and other contextual information that human readers easily and implicitly understand. The disclosed inventive concepts transform structured and semi-structured information along with textual content into a textual representation that allows generative models to better understand textual content and non-textual structured information present in document images.
Owner:KOFAX INC