5077 results about "Sentence" patented technology

The invention relates to the technical field of artificial intelligence, and discloses a bidding document generation method based on retrieval enhancement generation and a large language model, and the method comprises the steps: analyzing technical parameters, legal terms and score weights in a bidding demand document; retrieving matched historical bidding document fragments and technical specifications from the industry knowledge base, and generating a retrieval enhanced data set; fusing the data through a dynamic weight distribution algorithm and generating an initial bidding document draft; checking conflict terms based on the legal semantic knowledge graph and marking correction suggestions; and optimizing the bidding document structure and the key content according to the score weight. According to the method, an online learning mechanism driven by sentence vector matching, timeliness weight calculation and user feedback is adopted, so that the problems of inaccurate technical parameter extraction, low legal conflict detection efficiency and non-optimized scoring rules in the bidding document generation process are solved.

The invention relates to an AI Agent agent based on a big language model collaborative knowledge graph, which comprises a natural language dialogue module, a big language model module, an RPA SOP process knowledge graph module and an RPA execution engine, and is characterized in that the natural language dialogue module receives a natural language and converts the natural language into a structured query statement; the big language model module interacts with the natural language dialogue module and the RPA SOP process knowledge graph module respectively, and the big language model module understands user requirements, retrieves a knowledge graph according to query statements and generates an RPA process; the RPA SOP process knowledge graph module stores standard SOP knowledge of vertical business of a specific industry, and provides professional knowledge and standard constraints for knowledge query and reasoning; the RPA execution engine executes the generated RPA process; the invention further comprises an agent method and a storage medium. The RPA process knowledge graph is utilized to enhance the knowledge and reasoning ability of the large language model, RPA process steps meeting requirements are generated, and the RPA process generation accuracy and efficiency are improved.

The invention provides a knowledge graph construction and intelligent question and answer method and device based on deep learning. The method includes; obtaining target text data; information extraction is conducted on the target text data, entity relation data is generated, and the entity relation data comprises key data, entity data and relation data used for indicating the relation between entities; according to the entity relationship data, importing the target text data into a graph database to form a knowledge graph; obtaining an input question statement; the question sentence classification model is used for classifying the question sentences, question sentence features in the question sentences are determined, and the question sentence features comprise question sentence types and question sentence entity data; and retrieving text data matched with the question features in the knowledge graph as answer data of the question statements. According to the method, the public text information retrieval efficiency is improved, and the accuracy of intelligent question answering is improved.

The invention relates to the technical field of data processing, in particular to a method and system for processing data based on a large language model.The method comprises the following steps that based on inter-sentence punctuation positioning and part-of-speech tagging, sentence blocks are divided to generate functional partitions, themes and relational words are extracted to judge semantic chain starting points, a trigger index sequence is constructed, and logic jump points and breakpoint positions are recognized; and mapping the label structure to the language model output analysis deviation, and generating a label mapping combination list. According to the method, semantic turning nodes can be captured by analyzing the semantic direction change trend, the relation between the semantic turning nodes and verb and noun combinations is judged, the position of a trigger point of an actual information transfer effect is extracted, and the break point area of a semantic path is recognized through the positioning of key word starting and stopping blocks and the logical judgment of noun group cross combination; the path integrity has a clear fracture identifier, a traceable semantic mapping structure path is established in a language model, and the accuracy, coherence and hierarchy clearness of semantic reconstruction are enhanced.

To improve efficiency of idea proposal support.SOLUTION: A proposal support system executes: acquiring a specific first word from a co-occurrence network in which each first word of a first word group in a first sentence group including a first field name in at least one information source out of a first information source related to a first field and a second information source related to a second field different from the first field is a node, and a co-occurrence relation between two first words is a link connecting the nodes; extracting company names in the second field relating to the specific first word, from a second sentence group including a second field name and the specific first word from the at least one information source; associating the specific first word, a specific second word, and the company names in the second field, based on appearance information related to the specific second word that co-occurs with the specific first word in a second word group in the second sentence group; and performing output processing of outputting an analysis result in a displayable manner.SELECTED DRAWING: Figure 5

A behavioral authorship verification system captures and analyzes multi-modal behavioral patterns during content creation to authenticate human authorship. The system comprises a processor executing behavioral analysis modules that generate comprehensive behavioral fingerprints distinguishing genuine human authors from AI-generated content and impostor authorship. A sentence progression mapping module detects sentence boundaries and captures intermediate composition states including additions, deletions, and modifications. A multi-modal input analysis module monitors keystroke dynamics including flight time and dwell time while detecting paste events and input method transitions. A behavioral pattern recognition engine generates user-specific baselines from historical sessions and computes deviation scores using statistical distance metrics. An anomaly correlation module aggregates behavioral deviation signals using weighted fusion algorithms to detect sophisticated mimicry attempts. An authorship scoring engine synthesizes outputs into unified confidence scores while maintaining temporal authorship chains. The system enables real-time authorship verification during content creation rather than post-hoc analysis.

The invention discloses a large-model real-time voice text intention recognition method and system based on text prediction, and the method comprises the steps: obtaining the real-time voice data of a user, carrying out the real-time voice recognition processing through a streaming voice recognition interface, and obtaining a part of transcriptional text; inputting the partial transcription text into a mask language model for text prediction, and generating a plurality of high-credibility complete sentence candidates; based on the complete sentence candidates, the complete sentence candidates are input into a large language model in parallel for intention recognition, a corresponding intention result is obtained, and a mapping relation between the candidate sentences and the intention recognition result is established; and obtaining a sentence completely expressed by the user, calculating the similarity between the complete actual sentence and a plurality of high-credibility complete sentence candidates through a multi-level text similarity algorithm, selecting the candidate sentence with the highest similarity score, and directly obtaining a corresponding final intention recognition result based on the mapping relationship. The objective of the invention is to solve the technical problem of high response delay of an existing voice intention recognition system.

The invention provides a multi-knowledge-granularity text retrieval method and device for RAG, and the method comprises the steps: sorting an original text into a JSON file, carrying out the recursive character and semantic dicing processing, generating a target JSON file, and storing the target JSON file in a BM25 database and a vector database; when a user queries, preprocessing to generate a keyword list and a query embedded vector; searching for a target text in the BM25 database, and calculating a score of correlation with the keyword to determine a first to-be-selected text; determining a second to-be-selected text according to the query embedding vector; and performing duplicate removal processing on all the first to-be-selected texts and the second to-be-selected texts, and determining and outputting a final recommended text by utilizing a sorting model. By considering the problem of different search granularities, the keyword granularity is solved by adopting a BM25 algorithm. According to the semantic retrieval strategy combining sentence granularity and segment granularity, challenges of different text information lengths and different retrieval purposes are effectively handled, and therefore the advantages of traditional retrieval and semantic retrieval are fully utilized.

The invention discloses a large model knowledge base construction method based on multi-granularity retrieval. The method comprises the steps of obtaining a target text and analyzing a document structure, splitting and reorganizing text data according to three levels of titles, fragments and sentences, and constructing three levels of knowledge of the titles, the fragments and the sentences; using a large language model to construct a generative index as question-level knowledge according to the sentence-level knowledge; using a vector model to generate a first vector representing index keys of fragment-level knowledge and / or sentence-level knowledge, and a second vector representing index keys of title-level knowledge and / or question-level knowledge; and respectively storing the first vector and the second vector into a vector database, and storing the index values and the index types corresponding to the first vector and the second vector into a relational database. According to the method, multi-granularity document knowledge base construction is achieved, the expression modes of knowledge under different granularities are expanded, the accuracy of user query and knowledge matching is improved, and the problem that information is lost or incomplete in an existing method is solved.

A neural end-to-end system is provided for the face and voice preserving translation of videos. The system is a pipeline of multiple models that produces a video of the original speaker speaking in the target language with modified lip movement to match the target speech, while preserving emphases and prosody of the original speech, and voice characteristics of the original speaker. The pipeline starts with automatic speech recognition including emphasis detection, followed by the translation model. The translated text is then synthesized by a Text-to-Speech model that recreates the original emphases in the target sentence. The resulting synthetic speech is then converted back to the original speakers' voice using a voice conversion model. Finally, to synchronize the lips of the speaker with the translated audio, a generative model generates frames of adapted lip movements which are combined with the audio to produce the final output. The disclosure further describes several use-cases and configurations that apply these techniques to video conferencing, dubbing, low-bandwidth transmission, speech enhancement and assistive technology for the hearing impaired.

The invention relates to a text division method and device and electronic equipment. The method comprises the steps that sentences in a target text are recognized, the sentences are converted into sentence vectors, position codes for representing the positions of the sentences in the target text are constructed, the mapping relation among the sentence vectors, the sentences and the position codes is established, semantic clustering is conducted on the sentence vectors, multiple theme class clusters are generated, and a preset large language model is used for generating a plurality of theme class clusters based on the sentence vectors in the theme class clusters. The method comprises the following steps: generating a subject tag corresponding to each subject class cluster, converting the subject tag of the subject class cluster into a corresponding subject tag vector for each subject class cluster, calculating the similarity between the subject tag vector and a sentence vector in the subject class cluster, and dividing a target text based on the similarity and position codes. According to the scheme provided by the invention, the advantages of the semantic clustering algorithm and the large language model can be fully utilized, the recognition accuracy of each theme in the text is improved, and the accurate division of the text according to the theme is realized.

The invention relates to a method for constructing a subject textbook knowledge graph by using a large language model, and the method is realized through six steps: firstly, introducing a self-prompt framework, generating relation synonyms, synthesizing samples and sentence variants through three rounds of dialogues, and providing rich semantic guidance for subsequent relation extraction; secondly, guiding a large language model to accurately extract core knowledge point entities from teaching materials, exercises and PPT texts by means of a professional field instruction template; then, respectively extracting an attribute triple and a relation triple of the knowledge points by applying a multi-round dialogue mode and combining with a synthetic sample prompt; then, inputting the extracted triad into a verification module, and ensuring the accuracy through iterative verification; and finally, generating an entity embedding vector by utilizing an MPNet model subjected to subject knowledge fine adjustment, calculating entity similarity through a dynamic weighted pooling mechanism, judging entity pairs with high similarity, performing knowledge fusion if the entity pairs represent the same concept, and otherwise, reasoning a potential missing relationship and complementing the knowledge graph. According to the method, the knowledge graph of the course of the specific subject can be automatically constructed from the unstructured text efficiently and accurately, and powerful support is provided for teaching and learning of related subjects.

The invention provides a method for creating a structured document based on a deep learning model, and relates to the technical field of data processing, and the method comprises the steps: obtaining basic text information collected by a user, obtaining text data, fragmenting the text data, obtaining text fragmented data, and creating a structured document according to the text fragmented data. Analyzing the structures of the sentences in the paragraphs, determining keywords in the sentences, analyzing the logical relationship between the sentences in the paragraphs, associating the sentence keywords in the paragraphs, analyzing the association degree between the paragraphs in the chapters, identifying core keywords of the chapters, obtaining a chapter keyword data set, and analyzing the field involved in the text. The method comprises the steps of extracting field information of a text to obtain a text keyword data set, constructing a structured document model based on a graph neural network model, and inputting the text keyword data set and text data into the structured document model to obtain a structured document. According to the method, the structured document can be constructed through the deep learning model.

The invention discloses a video content semantic understanding and text description generation method based on deep learning, and relates to the technical field of multimedia information processing.The method comprises the steps that the semantic similarity of a text and a video frame is calculated through a CLIP model, related key frames are selected, and features are aggregated; respectively extracting audio, visual and semantic features; aligning different modal features by using self-attention, unifying dimensions of the LSTM, and then splicing and fusing; attention weights are calculated at a video level, a frame level and a channel level, and key information expression is enhanced; swin Transform encodes fusion features, and LSTM (Long Short Term Memory) decodes step by step to generate natural language description; and a text-video index database is constructed, and rapid retrieval is realized based on semantic similarity. According to the method, the mapping relation between the video features and the natural language is learned end to end through the deep learning model, dependence on a fixed template can be eliminated, and semantic description with various sentence patterns and coherent logic is generated.

The invention provides a long document semantic coherence processing method and device, a storage medium and computer device.The method comprises the steps that block coding is conducted on a long document through a sliding window converter, and the sliding window converter comprises a window dividing unit, a position coding unit and a converter coding unit; the window division unit adjusts block positions according to sentences and paragraph boundaries and sets overlapping areas between adjacent blocks; the encoded document content is stored and managed through a memory management module, the memory management module comprises a chapter-level memory pool and a gating memory unit, the chapter-level memory pool stores the document encoding content, and the gating memory unit maintains entities and event timelines; performing deep semantic understanding on the document content through a semantic processing module, and calculating a multi-dimensional attention weight capture dependency relationship between paragraphs; providing a retrieval result through a retrieval module; and generating semantically coherent output content through a content generation module. According to the scheme, the semantic coherence of long document processing is improved.

The invention relates to the technical field of knowledge extraction, in particular to a knowledge graph construction method and system based on a large model, and the method comprises the following steps: obtaining a current input statement of a user through a dialogue state tracker, inputting the statement into a BERT intention classification model for domain label analysis, behavior type recognition and emotional tendency detection, and outputting a three-dimensional classification vector; and extracting entity lexical items and relation predicates based on an LSTM sequence tagging device, and generating an original semantic structural body. According to the method, intention classification, behavior recognition and emotion detection are fused through three-dimensional semantic analysis, semantic comprehension granularity is improved, dynamic entity disambiguation is combined with a Manhattan distance threshold value and dialogue history tracking, semantic boundaries are defined to reduce anaphora ambiguity, and cross-modal alignment is enhanced through relation predicate hierarchical clustering and knowledge base dynamic matching; generative reply and semantic coherence reordering collaboratively keep topic continuation, and structured analysis and unstructured generation closed loop optimize semantic output and interaction fluency.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a set of large language models to determine a natural language response to a query. One of the methods includes receiving a query related to a document. The document is submitted to a first model along with a prompt to generate an outline of the document. The document is submitted to a second model along with a prompt to generate metadata of the document. At least a portion of the query, document metadata, and the document outline are submitted to a third model with a prompt to generate a natural language response to the query. A selected sentence from the natural language response is correlated to a document sentence. The natural language response is provided to the user with an indication that the selected sentence from the natural language response is correlated to the document sentence.

The invention discloses a business process rapid modeling method based on a large language model. The method comprises the following steps: preprocessing an input business process description text, and splitting complex sentences and composite sentences into simple sentences by utilizing a large language model; and extracting the fact types in the simple sentences in a chained manner, wherein the fact types comprise entities, events and event types. And giving a plurality of event relation sets with possible prediction according to the extracted event sets through a large language model, and combining the event relation sets with the event relation sets extracted in a chain manner to form an event relation pool. And using the event relationship as a gene by adopting a genetic algorithm. After the evolution process of the genetic algorithm, an event relation set with the highest fitness is filtered out from an event relation pool. And constructing a logical relationship between the fact type and the business process elements, and converting the extracted information into corresponding json data. The method comprises the following steps of: realizing conversion among structured data through a template, and converting json data into a business process execution language (BPEL) and a language for describing a graphic element of a BPMN (Business Process Execution Language). And finally, inputting the BPEL and a language for describing the BPMN graphic elements into business flow chart modeling software to generate a visual business flow chart. Through the above mode, the modeling efficiency can be improved, the modeling threshold can be reduced, and further customization and editing can be carried out in a professional modeling tool to meet specific requirements.

The invention discloses an intelligent demand structuring method and an intelligent demand structuring system, which are used for generating a structured demand document which can be used for subsequent software development based on business demand description of a natural language. For the simple requirement of a single module, one sentence input is adopted; for complex demands of multiple modules, a business modeling agent is called to carry out modeling understanding, natural language demands are converted into a business concept set, and the business concept set is further decomposed into specific structured demands by a demand structured agent. In the whole process, the user can adjust and refine the business software demand in real time through interaction with the business modeling agent and the demand structuring agent. According to the method, the structured demand document capable of being used for subsequent software development can be completed through natural language description, an efficient, flexible and intelligent new mode is provided for the structured demand of multi-field personalized service software and even software development, and the efficiency and quality of software development can be greatly improved.

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.

The invention provides a semantic enhancement adaptive partitioning method and system for natural resource large model questions and answers, and aims to solve the problems of difficulty in term boundary recognition, damage to semantic integrity and the like. According to the method, three core technologies including theme perception coarse-grained paragraph division, self-adaptive sliding window theme hierarchy division and embedded perception context self-adaptive text segmentation are fused. The system firstly analyzes a natural resource long text structure, identifies titles and theme levels and aligns associated contents; paragraphs are extracted according to a theme perception strategy and are subdivided into sentence sets according to grammar rules; an improved sliding window mechanism is adopted to divide sentences into window sentence block groups. The method is characterized in that a dynamic aggregation threshold mechanism is introduced, the semantic association degree between adjacent sentence blocks is calculated through an embedded perception context semantic segmentation technology, whether the sentence blocks are combined or not is judged by combining a similarity distribution change trend and a dynamic adjustment threshold, self-adaptive delimitation of semantic boundaries is achieved, and text blocks which are clear in structure and coherent in semantics are generated.

The invention discloses an intelligent report generation method and system based on multi-source heterogeneous data fusion, and particularly relates to the technical field of data fusion, and the method comprises the steps: constructing a fact anchor point containing a stable identifier in a fusion layer, and solidifying an aperture version signature and a time interval; packaging a screening condition, a sorting rule, an access plan, time window limitation and the like into a controlled context packet and freezing the controlled context packet into a unique fact source; in the range, generating sentences by using a limited template and writing sentence-level reference marks, so that each sentence can be traced back to a data slice and an evidence fragment; performing consistency verification according to a source, an aperture and time, performing conservative degradation on the attribution expression according to a consistency threshold value, and outputting a degradation strategy description; and finally, page two-way pointer and cross-sentence consistency recording and audit playback are realized through an evidence chain pointer table and a published version signature, and the problems of caliber drift, cross-window access and difficulty in evidence tracing are solved.

An intention recognition method includes: obtaining an input sentence; obtaining at least one first sentence-intention pair based on the input sentence, in which the first sentence-intention pair includes a candidate sentence similar to the input sentence and a candidate intention to which the candidate sentence belongs; generating first prompt information based on the at least one first sentence-intention pair; and obtaining a target intention to which the input sentence belongs by performing an intention recognition on the input sentence based on the first prompt information.

The invention relates to an intelligent short message template generation method and system based on a large language AI model, and the method comprises the steps: extracting cross-cultural communication frequency, sentence pattern preference analysis results and screen size adaptation data from social media interaction data and equipment use logs of target audiences, and generating a cultural background distribution matrix; identifying regional culture features in the culture background distribution matrix to obtain a taboo matching result; generating an expression habit preference matrix according to the updated culture background distribution matrix; generating a preliminary short message template according to the expression habit preference matrix and the symbol semantic mapping table, and outputting an adjusted template set conforming to message length control; analyzing the acceptability of the adjusted template set on the language conciseness requirement and the interactive button layout, and generating a new template set; evaluating a text alignment mode of the new template set; and screening candidate short message templates according to the information definition score. According to the invention, the accuracy and acceptability of cross-culture short message communication can be effectively improved, and the participation degree of audiences is enhanced.

The invention provides an illusion detection method and device based on semantic embedding and structure entropy detection. The method comprises the following steps: aiming at an input question, generating a plurality of possible answer sets by utilizing a trained language model; converting each answer into a vector by using a pre-trained sentence embedding model, and calculating cosine similarity between the answers so as to construct a similarity graph; representing the similarity graph through a coding tree, and calculating the structure entropy of each node to identify nodes with relatively high semantic uncertainty; dynamically adjusting a threshold value by adopting a moving average method to ensure that high-entropy output is marked as illusion in time; and the answers marked as illusion are eliminated, so that the accuracy of the output answers and the information consistency are ensured. According to the method, the performance of the model on complex problems is effectively improved, and the generation of misleading information is reduced. Preliminary experiments show that according to the method, the illusion output proportion is remarkably reduced on multiple data sets, and the semantic consistency and accuracy of generated answers are enhanced.

Improve the efficiency of writing documents. [Solution] The program causes the processor to execute the following steps: receiving from a first user a designation of a child or a group to which the child belongs as a target for generating sentence suggestions; identifying one or more images from among images recording activities related to child welfare stored in a database as images related to the child or group designated as a target for generation; generating a prompt including instructions including reading the situation of the identified image and generating a sentence suggestion related to the child or group designated as a target for generation based on the read situation; inputting the prompt including information about the image into the large-scale language model to obtain sentence suggestions from the large-scale language model; and presenting the obtained sentence suggestions to the first user.

The invention relates to the technical field of knowledge maps, in particular to a digital human knowledge map construction method for famous and old traditional Chinese medicine experience live inheritance, which comprises the following steps of: acquiring traditional Chinese medicine literature data, disassembling literatures sentence by sentence, cutting continuous statements into independent vocabulary units, and marking the grammatical effect of each vocabulary in the sentence; by analyzing a combination rule between adjacent vocabularies, multiple entities in a text are identified, and a literature entity set is generated. According to the method, through grammar labeling and context mode analysis, the accuracy and coverage of entity extraction are improved, and through combination of co-occurrence frequency and modification relation derivation, entity association interpretability and semantic network dimension optimization, dynamic weight calculation and attribute fusion, the self-adaptive optimization capability of the knowledge graph is achieved; according to the method, a matching degree calculation and closed-loop verification mechanism is adopted, the accuracy of clinical taboo recognition is improved, a term system and a dynamic evolution mechanism are structured, and a traditional Chinese medicine knowledge system considering deep semantic expression and persistent evolution is constructed.

The present disclosure provides a system for generating customized messages to a prospect. The system comprises: a data input module configured to receive prospect data, wherein the prospect data comprises data related to a prospect and data gathered from a plurality of sources; an input data processing module configured to select a subset of the data to create an input data; a first model trained to generate one or more sentences based on the input data; and a second model trained to determine whether the one or more sentences are unacceptable, wherein upon determining the one or more sentences are unacceptable, directing the input data processing module to select another subset of the data to create a new input data.

The invention particularly relates to a document abstracting method based on domain knowledge and a multi-granularity graph network, which comprises the following steps: S1, constructing a knowledge coding module, carrying out domain knowledge graph transfer learning, extracting triple structure features in combination with a capsule network, and generating a text entity coding module; s2, constructing a knowledge fusion module, converting a document text into a semantic vector, and adaptively fusing the semantic vector with external knowledge; s3, constructing a word-level semantic graph, and aggregating neighborhood information through a semantic graph attention mechanism to obtain word embedding representation containing context; s4, constructing a sentence-level semantic graph, performing self-attention calculation on the word-level semantic vector in the S3 to obtain semantic node representation of the sentence-level semantic vector, and performing feature aggregation on sentence-level nodes to obtain global semantic information of the document; and S5, constructing an output layer, and predicting according to the document feature vector in the S4 to obtain a final extraction type abstract result. The method has the advantages that redundant information in the document is removed, and ambiguity of text semantics is eliminated.

The invention relates to the technical field of artificial intelligence and the field of financial science and technology, and discloses a method for adjusting the playing speed of voice content in a video, and the method comprises the steps: obtaining a video file containing to-be-adjusted voice content, carrying out the voice recognition of an audio track of the video file, and converting the audio data of the voice content into text data; dividing the text data into a plurality of sentences or phrases; identifying keywords in each sentence or phrase, performing emotion content classification on the sentences or phrases containing the keywords, and determining the importance level of each sentence or phrase; according to the emotion content and the importance level, adjusting the playing speed of the corresponding voice content, and generating adjusted audio data; aligning the adjusted audio data with the video image to generate synchronous audio and video data; and a final video is generated. Through automatic voice recognition, sentiment analysis and playing speed adjustment, the steps of manual participation are reduced, and the video editing efficiency is greatly improved.