3835results about "Text processing" patented technology

The invention discloses a hierarchical semantic-driven retrieval enhancement generation method and system, a natural hierarchical relationship and a semantic boundary of a document are effectively reserved by constructing a tree hierarchical structure based on a document chapter title, and a recursive semantic boundary splitting strategy is adopted to refine overlong text nodes, so that the semantic integrity is ensured, and the retrieval enhancement generation efficiency is improved. And the model input length limitation is met, and the semantic information is prevented from being lost. Meanwhile, node knowledge point extraction and abstract generation are achieved through a large language model, top-down multi-level title path transmission and bottom-up content aggregation are combined, the structural perception and semantic expression ability of nodes is enhanced, and in the retrieval stage, based on similarity distribution of query and node semantic expression, an adaptive retrieval threshold value is dynamically calculated, and the retrieval efficiency is improved. A fixed top-k retrieval strategy is replaced, intelligent screening of different query and hierarchical nodes is achieved, information coverage and redundancy suppression are balanced, and retrieval efficiency and accuracy are remarkably 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.

A digital documentation system for preparation of engineering documents utilizing one or more artificial intelligence (AI) algorithms is provided. The system includes a user interface for selecting and populating templates with data, and one or more AI algorithms for creating and recommending templates, and preparing documents based on the recommended templates. The system uses natural language processing and semantic analysis algorithms to understand the content of the templates, documents, and associated engineering data, and to generate and recommend relevant templates to the user based on user prompts. The system also uses machine learning and predictive modeling and decision-tree algorithms to assist with the preparation of documents, by generating suggestions for data fields and values based on the user's previous inputs and the overall context of the document and available engineering data, including model data and metadata from digital models accessed in a zero-trust framework.

The present invention relates to the technical field of knowledge graph completion tasks, and particularly relates to a knowledge graph link prediction method. The method comprises: using a precoding model to obtain an embedding layer vector, and constructing a corresponding masked triple; adding a corresponding position code to each element in the masked triple, so as to obtain a corresponding input sequence, inputting the input sequence into a trained main masking model, and outputting an entity classification probability; and on the basis of the entity classification probability, predicting potential candidate entities. The method further comprises: concatenating semantic information corresponding to the embedding layer vector and structural information obtained by an embedding model, so as to obtain fused head entity and relation representations, and constructing a corresponding fused masked triple; and adding a corresponding position code to each element in the fused masked triple, so as to obtain a corresponding fused input sequence. The present invention uses a precoding method, thereby effectively reducing the training burden on a model, and improving the inference speed of a model; and a fusion module is used before inputs are fed into a main masked model, thereby ensuring the integrity of textual description information and improving prediction accuracy.

Embodiments of the present disclosure provide a report generation method and system, an electronic device, and a storage medium. The report generation method comprises: acquiring requirement text information of a report to be generated in a target application scenario; performing requirement intent recognition on the requirement text information, to acquire a report parameter matching the report to be generated; on the basis of the target application scenario, selecting and arranging a preset intelligent agent, to obtain an intelligent agent call chain; on the basis of the report parameter, performing chain-type calling on the preset intelligent agent in the intelligent agent call chain, to generate a report matching the requirement text information. The present method can automatically and quickly generate a report matching a user requirement, effectively increasing report generation efficiency. Using the present method to generate a report does not require manual data acquisition and analysis; efficiency is higher, and costs are lower.

The invention provides a multi-modal knowledge extraction method and system based on multi-agent collaborative optimization, and relates to the technical field of knowledge extraction, and the method comprises the steps: carrying out the multi-modal deconstruction of an original document to be extracted; constructing a multi-modal agent, respectively executing feature extraction and preliminary knowledge extraction, and outputting a single-modal multi-component system; based on a cross-modal knowledge graph, mapping information of different modals to a unified semantic node, and establishing cross-modal association and analyzing a logic chain through a graph neural network and a causal reasoning module; dynamically allocating resources according to the importance of map nodes, and screening structured knowledge; and through confidence analysis and node traceability evaluation, an intelligent agent cooperation mechanism is optimized, and increment correction is carried out on a result. According to the method and the device, the technical problem of low knowledge extraction accuracy and efficiency caused by insufficient multi-modal knowledge collaborative mining capability due to knowledge extraction of literatures by adopting a single agent in the prior art can be solved, and the knowledge extraction quality and efficiency are improved.

The invention relates to the technical field of machine vision, and discloses a machine vision-oriented cross-modal image-text analysis method, which comprises the following steps of: partitioning an input image to generate an image block sequence; inputting the image block sequence into a visual converter for multi-scale feature extraction, and generating target visual features; encoding the input text to generate a target text feature; inputting the target visual features and the target text features into a deep reconstruction bottleneck network for compression alignment, and generating a cross-modal compression vector; and inputting the cross-modal compression vector into a large language model to generate cross-modal decoding information, so that cross-modal redundant information can be effectively filtered, compact shared semantic representation can be learned, the information integrity of the compression process is ensured through bidirectional reconstruction verification, cross-modal semantic alignment is realized, and the method has the advantages of high efficiency and high reliability. Omnibearing cross-modal content generation from the whole to details is achieved, and the requirements of different application scenes are met.

The invention discloses a report chart automatic generation method based on natural language analysis and data query, which comprises the following steps: acquiring a natural language text, and constructing a slot set and an initial semantic fragment; executing consistency verification and ambiguity identification, and constructing a semantic framework; executing field standardization and mode alignment, generating a data query statement and establishing a traceability chain identifier; querying a target database to obtain an original data set, completing data quality self-correction, and generating a cleaned data set; calling an improved Mamba model to construct a constraint judgment matrix and outputting a target chart subset; generating a chart description grammar and an image annotation template, and executing image rendering, feature point recognition and image sidebar construction; and performing layout optimization and double compilation, and outputting a structured report file. According to the method, the chart generation automation level and the report compiling efficiency are improved, and the accuracy, traceability and specialty of the output content are ensured.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a natural language driven table processing method, device, equipment and medium. And generating and executing an operation action by utilizing the reinforcement learning strategy network, generating a reward signal according to execution result data and user feedback information, storing the state vector representation, the target table operation action and the reward signal into an experience playback queue, and updating network parameters of the reinforcement learning strategy network based on historical data in the experience playback queue. According to the method, the state vector is constructed through the reinforcement learning strategy network in combination with the natural language instruction and the table context, and the operation strategy is continuously optimized according to the operation result and the user feedback, so that intelligent understanding and action planning of the spreadsheet operation intention are realized, and the data processing efficiency and the interaction intelligence level of non-professional users are improved.

The invention provides an official document key abstract generation method and system based on multi-modal feature extraction, and relates to the technical field of multi-modal artificial intelligence generation, and the method comprises the steps: firstly obtaining text modal data, image modal data and table modal data of a to-be-processed official document, then carrying out the hierarchical semantic analysis processing of the text modal data, and obtaining a to-be-processed official document key abstract; the method comprises the following steps: generating a text semantic feature set, performing visual element extraction processing on image modal data, generating an image feature set, performing structured analysis processing on table modal data, generating a table feature set, and performing cross-modal alignment processing on the text semantic feature set, the image feature set and the table feature set. According to the method, the dynamic association feature sets among the text semantics, the image elements and the table elements are determined according to the text semantics, the image elements and the table elements, the three feature sets are subjected to multi-modal fusion processing according to the feature sets, the target abstract content of the to-be-processed official document is generated, complementarity of multi-modal information in the official document is fully utilized, and the generated abstract is more complete, accurate and targeted.

The invention discloses a CAD drawing engineering quantity automatic identification and calculation method based on a large language model and image segmentation, and the method comprises the steps: extracting project annotation information in a CAD drawing, understanding and reasoning a project introduction through a large language model, and carrying out the structural expression of the project annotation information; the method comprises the following steps: preprocessing a graph in a CAD drawing by utilizing computer vision, analyzing a pipeline drawing of the CAD drawing by utilizing machine learning, identifying the type and position of a component in the pipeline drawing, and realizing semantic segmentation and instance segmentation; and fusing the structured project annotation information, the semantic segmentation result and the instance segmentation result, counting and calculating the project amount of each pipeline component in the CAD drawing image, and outputting a report according to classification. According to the method, OCR recognition, natural language processing, graph semantic recognition, engineering logic calculation and other technologies are integrated, the CAD drawing processing efficiency and the engineering quantity calculation accuracy are greatly improved, and intelligent support is provided for design, construction, drawing examination, budget and other links.

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.

A large language model (LLM) message generation system and method tor generating a response to a user message. The method includes: obtaining a text document specified by a user; chunking the text document into a plurality of chunks; generating text gloss data for each of the plurality of chunks based on the chunk and a predetermined prompt; storing the text gloss data for each chunk into a vector data store along with an identifier for the chunk and / or tine chunk itself; receiving a user message; querying the vector data store with a vector data store query, wherein the vector data store query is generated based on the user message; obtaining chunk(s) based on querying the vector data store with the vector data store query; generating a language model input based on the one or more identified chunks; and generating a response message based on inputting the language model input.

Provided in the present invention is a parameter-efficient large-language fine-tuning federated learning framework, comprising the following steps: performing modeling on LoRA adapters of different edge clouds; since different weights exhibit different average performances on the LoRA adapters, using singular values to quantify the importance of the weights, and therefore, before each round of independent training of the LoRA adapters using N edge clouds, using a matrix singular value to decompose a BA matrix in the LoRA adapter for each trainable weight; configuring heterogeneous LoRA adapters on the basis of the importance of the weights; and using different numbers of quantization bits to quantize a pre-trained model, and performing high-precision inverse quantization on the pre-trained model only when matrix multiplication is executed, wherein the pre-trained model is quantized to the maximum number of quantization bits on the basis of the memory budget of the edge clouds. The present invention has the following beneficial effects: the present invention determines the optimal fine-tuning model structure, thereby improving the performance of LLM fine-tuning, and adapts to heterogeneous and resource-constrained edge clouds.

A large language model (LLM) may be used to classify an input into one of a plurality of categories. However, given the machine-learning operation of the LLM, the output of the LLM does not represent a definitive statement, but is based on probability computations of the machine learning model. Therefore, the classification performed by the LLM might not be correct. Classification into the wrong category by the LLM results in downstream technical problems. In some implementations, when an LLM generates a response that classifies an input, one or more probability values associated with a token that forms the basis of the response may be used to determine a confidence value. The confidence value is indicative of confidence in the classification performed by the LLM. An action may be taken based on the confidence value.

The invention relates to the field of computer vision, and particularly provides a table recognition reconstruction method and system, a terminal and a medium, and the method comprises the steps: firstly decomposing a large-size table image into a plurality of overlapped sub-images, and carrying out the table structure detection and OCR character recognition of each sub-image through parallel recognition; then, sub-graph recognition results are integrated through a coordinate mapping and confidence coefficient weighted fusion algorithm, and boundary errors are eliminated; then, automatically distinguishing common cells based on an area clustering algorithm, merging the cells and a header region, and reconstructing a complete table logic structure; further understanding header semantics through a natural language model and repairing identification errors; and finally, realizing intelligent splicing and standardized output of the cross-page table. According to the method, the memory limitation of the traditional OCR technology is broken through, an oversized table can be processed, the recognition accuracy of a complex structure is improved, and the digitization efficiency of professional documents such as financial statements and engineering drawings is improved.

The invention relates to the technical field of large model intention understanding, and discloses an APP dialogue type service reaching method and system based on large model intention understanding. The method comprises the steps of receiving a natural language text input by a user on an APP dialogue interface and performing large model semantic analysis to obtain service semantic data; inputting the business semantic data into an intention recognition model for business intention understanding to obtain business intention data; performing multi-agent cooperative process planning to obtain execution process data; carrying out interactive confirmation on the service parameters to obtain service execution parameters; transmitting the service execution parameters to corresponding service tool interfaces for calling execution to obtain a service tool calling result, and performing intelligent analysis and card rendering on the service tool calling result to obtain display card data. According to the method, the real business intention of the user is accurately understood, and the problems of execution efficiency and stability of a traditional single interface calling mode in a complex business scene are solved.

A document is analyzed to identify attributes of the document. A set of statistical measures are calculated for each of the formatting attributes. A correlation between these statistical measures and elements of the document are identified. A hierarchical relationship is determined between the elements of the document. Data from the document is split into chunks using the hierarchical relationship. A representation of the document that includes the hierarchical structure is then generated. The representation is stored in a data store as a vector usable by a machine learning model to perform a query on the document according to the hierarchical structure.

The invention relates to the technical field of artificial intelligence and language learning, in particular to a multi-modal language learning auxiliary system and method based on artificial intelligence, and the system comprises a multi-modal input module, a cross-modal feature fusion module, a dynamic adaptive learning module and an interactive feedback generation module. Wherein the multi-mode input module is used for receiving original text data, original image / video data and original voice data; the cross-modal feature fusion module is used for extracting a visual feature vector and a semantic coding vector and generating a cross-modal joint feature vector; the dynamic adaptive learning module is used for generating dynamic scene parameters; and the interactive feedback generation module is used for outputting a multi-mode feedback data packet through a prompt learning engine. According to the method, by fusing multi-modal feature alignment and dynamic context parameter modeling, linkage generation of grammar, culture and pronunciation feedback is achieved, and the context understanding ability and interaction feedback precision in the language learning process are improved.

According to the agent construction method and the multi-agent cooperation method provided by the invention, the agent parameter configuration file is acquired, and the agent basic information, the ECA rule, the behavior tree path index and the performance function parameter configuration are loaded from the agent parameter configuration file; the knowledge hypergraph is adopted to aggregate agent basic information, ECA rules, behavior tree path indexes and performance function parameter configuration, and a dynamic knowledge network with semantic association is obtained; and after a prompt word used for calling the large language model is dynamically generated based on the dynamic knowledge network, the large language model is driven to generate an executable code, and when the executable code passes verification, an agent corresponding to the agent parameter configuration file is obtained. And then, aiming at a received user instruction, performing task processing by adopting the constructed multi-agent. Therefore, the autonomous decision-making capability and the dynamic adaptability of the intelligent agent are enhanced, and higher flexibility and expansibility are achieved.

The invention discloses a method for converting a natural language into a low code based on multi-modal reinforcement learning, which comprises the following steps of: performing word segmentation, embedding and multi-layer feature extraction on a natural language instruction input by a user, combining a self-attention mechanism and a graph attention mechanism, extracting and optimizing an original semantic feature vector, and automatically identifying a business field; semantic relationship triples in the domain knowledge graph are fused, and a multi-modal semantic alignment and context enhancement strategy is adopted, so that the accuracy and stability of semantic representation are remarkably improved; when semantic drift or ambiguity is detected, a multi-candidate correction mechanism is triggered to obtain a better analysis result, and the robustness of semantic understanding is enhanced; and finally, mapping an analysis result into an instruction which can be identified by a low-code platform, automatically generating a code structure, continuously optimizing a semantic model and a knowledge graph based on user feedback, realizing adaptive learning, and improving the conversion efficiency and quality from a natural language to codes.

The invention relates to the technical field of automatic data analysis, in particular to an intelligent data report generation method and system based on an MCP protocol. The method comprises the following steps: constructing a semantic intention vector through a context semantic structure according to an obtained natural language instruction of a user; constructing a semantic task path graph based on the semantic intention vector by utilizing a knowledge graph; according to the constructed semantic task path diagram, performing intention path and tool capability mapping based on an MCP protocol; constructing a task flow based on an MCP protocol and performing task scheduling optimization; carrying out data source unified modeling based on the constructed task flow, and generating a stable and controllable calculation task flow; and visual expression generation from data to graphs is realized through an intelligent recommendation and structural modeling mechanism. According to the method, a semantic-driven MCP plug-in tool chain and a chart capability component index are constructed, so that a full-automatic closed loop from a natural language intention to data analysis and chart generation is realized, and meanwhile, the use threshold of non-technical users is reduced.

The invention provides a financial statement generation method and system based on cloud computing, and the method comprises the steps: collecting multi-source data of an internal business system of an enterprise through a centralized data integration platform based on a cloud computing environment, carrying out the classified storage, and constructing a data set; verifying the data set, and obtaining key index fields related to financial statement generation in the verified data set; performing grouping calculation on the key index fields by adopting a data aggregation algorithm to form a financial data summarization result; dynamically mapping the financial data summarization result by adopting a report generation engine, and matching with a preset financial report template to obtain a report data framework; and performing secondary verification and encryption on the report data framework to obtain a final financial report. According to the technical scheme, automation, real-time performance and unmanned performance of financial statement generation are realized through full-link innovation of edge intelligent acquisition, streaming processing, incremental aggregation and zero-trust security.

The invention discloses a PDF (Portable Document Format) document content processing method and device, equipment, a storage medium and a program product, and relates to the technical field of document structured processing. Preprocessing the PDF document to obtain a to-be-processed data set corresponding to each page of the PDF document; determining the page type of each page of the PDF document based on all the to-be-processed data sets and the image of each page of the PDF document; and based on the to-be-processed data set corresponding to each directory page and the image of the directory page, extracting a hierarchical structure relationship of each title data in the directory page, and constructing a directory tree. And matching the title data of the directory page and the title data of the non-directory page based on the semantic similarity and the text similarity between the title data of the directory page and the title data of the non-directory page, and correspondingly filling the content data under each title node of the directory tree according to a matching result to obtain a structured representation result of the PDF document. According to the method and the device, the semantic reduction degree and the structural quality of the PDF document are improved.

The invention discloses a contract auditing method and device based on a large model, equipment and a storage medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: analyzing a target contract file based on an optical character recognition technology and a natural language processing technology, and generating a target structured analysis fragment corresponding to the target contract file; constructing a contract relation knowledge graph based on the target structured analysis fragment by using the target large model, and generating a target structured data table; verifying each contract term in the target structured data table based on a dynamic rule engine, and generating an early warning report based on a verification result; performing risk assessment on contract terms in the target structured data table based on the target domain knowledge base, the target large model and the contract relation knowledge graph to generate risk data; and generating a revision suggestion based on the early warning report and the risk data by using the target large model, and revising the target contract file based on the revision suggestion. According to the invention, the automation level and accuracy of contract auditing can be improved.

A document preparation method involves creating a hierarchical representation of an input document without summarizing or omitting any content. The method uses a generative language model to generate the hierarchical representation and stores it in a repository for later use by a client generative language model. This allows for more accurate and complete generation of text, enabling the use of retrieval units to enhance the output of the client generative language model while efficiently exploiting its limited context window.

The invention relates to an RAG-based voucher classification method, a medium and equipment, and the method comprises the steps: receiving digital image data of a to-be-classified voucher, carrying out the multi-modal optical character recognition processing to generate a structured OCR result, extracting a text semantic feature vector and a visual layout feature vector based on the structured OCR result, carrying out the fusion of the text semantic feature vector and the visual layout feature vector to generate a multi-modal query vector, and carrying out the classification of the to-be-classified voucher. Similar samples and semantic similarity scores and category metadata thereof are obtained through approximate nearest neighbor retrieval, after an initial candidate category list is generated, key field values are extracted for each candidate category, evidence credibility scores are calculated, comprehensive confidence scores are generated by fusing the semantic similarity scores and the evidence credibility scores, reordering is conducted, and a candidate category list is obtained. And finally, selecting a classification decision path according to the score distribution, and outputting a classification result and an interpretability report. The accuracy and robustness of voucher classification are effectively improved, and complex voucher scenes with changeable formats and fuzzy semantics can be processed; and the interpretability and reliability of the classification decision are enhanced.

The invention discloses a document review method and device based on the full life cycle of science and technology projects and a medium, belongs to the technical field of document review, and solves the problem of how to improve the accuracy of normative review of science and technology project documents. According to the method, project document content is sequentially decomposed into field type analysis, specification requirement analysis and content specification analysis on the basis of the thinking chain technology, each item of analysis depends on the result of the previous item of analysis, and a complete path of conventional review is constructed step by step; the method comprises the following steps: analyzing whether a conflict and a logical conflict exist between a current to-be-audited project document and a historical document or not by utilizing a retrieval generation enhancement technology, and obtaining a plurality of fragments associated with to-be-audited fragments of the document from the documents in different life cycles; and ranking of possible useful fragments is provided for the large language model, an examination result is given, logic conflicts and contradictions among the documents are identified and solved, and the examination accuracy is improved from the aspects of consistency and logicality of the documents to be examined and historical documents.

A computing system including one or more processing devices configured to receive prompt generation instructions that specify an initial prompt and a prompt evaluation criterion. In each of a plurality of iterations of a prompt generation loop, the one or more processing devices are further configured to generate candidate prompts at least in part at a machine learning model. The candidate prompts are generated based on a current-iteration prompt that is initialized as the initial prompt in a first iteration. As specified by the prompt evaluation criterion, the one or more processing devices are further configured to compute respective evaluation scores associated with the candidate prompts. Based on the evaluation scores, the one or more processing devices are further configured to replace the current-iteration prompt. The one or more processing devices are further configured to output a final prompt generated in a final iteration.