142 results about "Structured content" patented technology

Embodiments described herein relate to systems and methods for automatically generating content, generating API requests and / or request bodies, structuring user-generated content, and / or generating structured content in collaboration platforms, such as documentation systems, issue tracking systems, project management platforms, and other platforms. The systems and methods described use a network architecture that includes a generative interface panel having multiple automated assistant services. Each assistant service may access a prompt generation service and a set of one or more purpose-configured large language model instances (LLMs) and / or other trained classifiers or natural language processors used to provide generative responses for content collaboration platforms.

The invention discloses a financial document automatic auditing method and device and a medium, and relates to the technical field of financial reimbursement auditing. The method comprises the following steps: receiving a financial document to be audited and an associated attachment document, respectively extracting a first entity set, and extracting a second entity set from unstructured content; constructing a dynamic knowledge graph state space based on the entity set, wherein the dynamic knowledge graph state space comprises an entity vector generated by an entity embedding algorithm and a relation vector generated by a relation coding algorithm; defining a reinforcement learning action space, wherein the reinforcement learning action space comprises three types of atomic operations of newly adding and deleting a triple and adjusting confidence; in combination with the real-time document flow, the historical case library and the audit result data, dynamically evolving the knowledge graph through atomic operation, and calculating a value return value of each operation; pre-judging accumulated return values of different operation sequences by utilizing a Monte Carlo tree search algorithm, and pruning a low return sequence; executing the optimized operation sequence to update the knowledge graph; and finally, based on the updated atlas, triggering a logic verification rule to generate an auditing result.

The invention discloses a declarative knowledge construction method and device for semantic and situational knowledge collaborative modeling, computer equipment and a readable storage medium, and relates to the field of data processing.The method comprises the steps that firstly, a multi-modal document is analyzed, a chapter abstract is extracted, and structured content is obtained; entities, events and multi-modal knowledge points are extracted from the structured content, and cross-modal fusion is carried out on the entities, the events and the multi-modal knowledge points; carrying out anaphora resolution based on the fused knowledge points, and constructing a double atlas containing a knowledge atlas, a affair atlas and a four-dimensional relation triple; clustering the double maps to obtain a theme community, and performing association mapping on the community, the triple and the entity event, the chapter abstract and the multi-modal knowledge point to form association knowledge; vectorizing the associated knowledge and establishing a vector knowledge index; and carrying out compression ratio and accuracy evaluation on the knowledge through an evaluation system, and feeding back and optimizing the whole knowledge construction process. According to the method, multi-modal knowledge deep fusion and semantic scene collaborative modeling are realized, and the knowledge structuring degree and the application reliability are improved.

The invention provides a report generation method and system based on a multi-agent architecture, and the method comprises the steps: firstly receiving and analyzing a report generation instruction, obtaining a theme demand, a framework specification and an initial reference material, then starting a multi-agent cooperation framework, generating an agent task distribution table, and generating an agent task distribution table; and the resource retrieval agent executes network resource directional retrieval according to the task allocation table to generate an associated resource set, and the content extraction agent performs structured conversion on the associated resource set and the initial reference material to obtain a structured content unit with chapter codes. The method comprises the following steps: performing module classification and logic series connection on a structured content unit by a report integration agent in combination with a framework specification to generate a report first draft, and finally performing content verification and optimization on the report first draft by a multi-agent collaborative framework to generate a final report text conforming to the framework specification, thereby realizing automation, intellectualization and high efficiency of report generation. And report quality is improved.

The invention discloses a method for creating and correcting a large model fine tuning data set, and relates to the technical field of large models. The method comprises the following steps: converting received structured and unstructured texts into structured content units in a unified format; generating and distilling an initial question and answer pair by using a teacher model taking a pre-trained large language model as a core; screening out high-quality question and answer pairs according to a quantitative evaluation system containing correlation, accuracy and integrity dimensions; performing diversified optimization on high-quality question and answer pairs by applying a generalization strategy and multi-round distillation, and performing dynamic regulation and control based on language feature difference to avoid content homogenization; and finally, guiding the teacher model to generate ternary structure data containing a thinking chain, and executing a verification and self-correction algorithm so as to generate a final fine tuning data set containing a verified reasoning process.

The invention provides a regional wind field multi-source heterogeneous work order data fast structuring system fused with a large language model, which comprises a plurality of modules, and is characterized in that a data input module receives various work order images; the OCR layout recognition module comprehensively recognizes the data, extracts key information, determines a spatial position and outputs text fragments with coordinates and layout anchor point information, and the rule field extraction module recognizes format category fields from the text fragments and calculates rule matching confidence; the semantic field recognition module recognizes descriptive fields from unstructured content and outputs related confidence information, the fusion decision module calculates final confidence of field candidates according to a predetermined function and judges output or complementation according to a threshold value, and the data consistency verification module is connected with an asset database to verify key information. The data complementation module generates complementation candidates and confidence coefficients, the man-machine collaborative closed-loop module pushes suggestions and receives feedback, and the result output module outputs standardized data. According to the method, the multi-source heterogeneous work order data can be effectively processed.

The invention provides a multi-modal content generation method and device, electronic equipment and a storage medium. The method comprises the steps of receiving a document uploaded by a user and performing content extraction; performing block analysis and semantic recombination on the extracted content to generate a PPT text outline and a corresponding explanation script; according to the PPT text outline, matching or dynamically generating a visual material to obtain a first edition PPT; the initial edition PPT is subjected to iterative optimization, the optimized PPT and the explanation script are synthesized to obtain an explanation video, complex structured documents or unstructured content can be processed, it is ensured that the generated outline is clear in organization and accurate in content, and multi-modal content meeting visual aesthetics is output through iterative optimization.

The invention discloses a cross-platform content generation and distribution method based on a multi-modal AI, and belongs to the technical field of cross-platform content generation and distribution, and the method comprises the steps: carrying out the content analysis and feature extraction of an original material based on a multi-modal AI model, and generating a structured content label and a semantic vector. By combining a vector matching degree formula of target portrait features and platform features, an adaptation strategy is dynamically generated, it is ensured that content not only conforms to platform rules, but also can accurately reach a target group, the conversion rate and user viscosity are finally improved, visual, text and semantic vectors are aligned through a Transform multi-modal fusion model, a cross-modal joint representation vector is generated, and the user experience is improved. And in combination with an adversarial generative network, differentiated variants of the same theme are generated in batches, and a content diversity score mechanism ensures that generated contents are balanced between creativity and compliance.

The invention provides a multi-modal data archiving processing system based on cloud computing, and relates to the technical field of data processing, and the system is used for obtaining an archiving request and an archiving task, determining an archiving type, a processing priority and a task number according to the archiving request and the archiving task, recording a memory identifier, an execution path and a cache address of a processing node, and storing the memory identifier, the execution path and the cache address of the processing node; the method comprises the following steps: extracting a structured field group and an unstructured content block of an archiving task, mapping the structured field group according to fields to generate a structure reference table, segmenting the unstructured content block according to a time sequence to generate a content time stream, recording each field mapping and time segmentation operation, and determining a reference relationship between each field mapping and time segmentation operation and a processing node; and determining a task number, a resource state and a data fragment of each processing node to obtain state anchoring data, combining the structure reference table and the content time stream with the state anchoring data into a double-layer archiving component, and archiving the double-layer archiving component. According to the method, content backtracking and operation backtracking can be carried out on the multi-modal data archiving process.

The invention relates to the technical field of auxiliary writing systems, in particular to a structured auxiliary writing system based on multi-agent collaboration. The system specifically comprises a writing task demand analysis and modeling module, a multi-agent system architecture construction module, a writing task disassembly and subtask distribution module, a multi-source knowledge retrieval and integration module, a structured content generation module, a format specification and quality evaluation module, a logic verification and content adjustment module and a user feedback iteration and model optimization module. The writing task demand analysis and modeling module firstly performs surface analysis on a writing task of a user, determines the type, theme, target audience, core demand and quality requirement of the writing task, and converts a fuzzy writing demand into a quantifiable and executable structured task model; according to the invention, the limitation of a traditional writing mode and an existing single-function auxiliary tool is solved.

The invention discloses a PPT exporting method, device and equipment based on an HTML page and a medium, and is applied to the technical field of computers. The method comprises the steps that the content type of a front-end page constructed based on the HTML is recognized; calling a native interface of the slide generation tool to export the structured content of the front-end page to the PPT; using a snapshot technology to render the three-dimensional model of the front-end page after the view angle is selected to obtain a rendering result, converting the rendering result into an image and embedding the image into the PPT; and rendering decorative chart elements of the front-end page by using a delay rendering technology, intercepting an image of a corresponding area after rendering, and exporting the intercepted image to the PPT. According to the method, high-fidelity, high-automation, editable and visually consistent multi-source heterogeneous content PPT export is realized, and a high-quality migration path from Web visual content to a PowerPoint presentation document is effectively opened.

The invention discloses a multi-modal unstructured content association retrieval method, which comprises the following steps of: performing feature extraction on multi-modal data to obtain features of the data in different modals; the multi-modal features are aligned, and multi-modal alignment features are obtained; random masking is carried out on the multi-modal alignment features, the multi-modal alignment features are sent into a cross-modal self-attention model to be fused, and multi-modal fusion feature vectors after masking are obtained; extracting enhanced features of each image; processing the enhanced features through a cross attention network to obtain cosine similarity between different images; performing image feature matching to obtain an image association result; a retrieval text is input into a large language model to obtain text features, through a multi-modal data embedding space, the most similar image is matched by using cosine similarity, and a retrieval result of the image is obtained. According to the method, the accuracy and the stability of multi-modal feature fusion are improved, and the accuracy and the efficiency of image retrieval are improved.

A method includes accessing a structured content item from a first database and event data from a second database, the event data including sets of event attributes in a multi-dimensional namespace and associated with a respective point in time; determining a relevancy profile characterizing a metric of relevancy of the structured content item over a respective time interval, the metric of relevancy including a distance in the multi-dimensional namespace between attributes associated with the structured content and the sets of event attributes; generating, using the relevancy profile, second digital content including a subset of the structured content item; and providing the second digital content for rendering on a device. Related apparatus, systems, techniques and articles are also described.

Embodiments described herein relate to systems and methods for automatically generating content, generating API requests and / or request bodies, structuring user-generated content, and / or generating structured content in collaboration platforms, such as documentation systems, issue tracking systems, project management platforms, and other platforms. The systems and methods described use a network architecture that includes a search and chat generative interfaces, which may be used to produce generative answers, identify relevant content, and take actions within a respective content collaboration platform.

The invention relates to the technical field of digital network broadcasting, in particular to a multifunctional integrated digital network broadcasting system based on an intelligent algorithm. Comprising a multi-modal data acquisition module, a broadcast content generation module, a broadcast scheduling decision module, an abnormal interference suppression module and a terminal collaborative feedback module. The multi-modal data acquisition module collects multi-source information of a coverage area in real time. And the broadcast content generation module performs intelligent clustering analysis based on the information to generate structured content. And the broadcast scheduling decision module adopts a graph attention scheduling algorithm to optimize a scheduling strategy. And the abnormal interference suppression module identifies an interference source by using a residual convolutional network, and repairs an interfered signal through a recurrent neural network. And the terminal collaborative feedback module executes playing and data feedback, and dynamically adjusts receiving parameters and pushing strategies by means of federal reinforcement learning. The intelligent level, the adaptability, the user satisfaction and the overall service efficiency of the digital network broadcasting system are remarkably improved.

The present application relates to the technical field of artificial intelligence, in particular to a video content understanding method and system based on artificial intelligence, which first acquires a video scene unit set of a video to be understood arranged in time sequence and containing scene element and object behavior information; then establishes a semantic behavior association graph of scene element information and object behavior information for each scene unit; further generates a hierarchical understanding process containing scene element semantic association analysis and object behavior logical association analysis based on the semantic behavior association graph; dynamically optimizes and adjusts the hierarchical understanding process according to the analysis result; and finally outputs a structured content understanding result containing scene semantic description and object behavior logical description based on the optimized process, so as to comprehensively, deeply and dynamically understand the video content.

Embodiments described herein relate to systems and methods for automatically generating content, generating API requests and / or request bodies, structuring user-generated content, and / or generating structured content in collaboration platforms, such as documentation systems, issue tracking systems, project management platforms, and other platforms. The systems and methods described use a network architecture that includes a prompt generation service and a set of one or more purpose-configured large language model instances (LLMs) and / or other trained classifiers or natural language processors used to provide generative responses for content collaboration platforms.

The invention relates to the technical field of electronic bidding systems, in particular to an electronic bidding system and method based on XML structured data, and the system comprises a structured content dividing unit which divides bidding content information into a plurality of segments and converts the segments into corresponding XML segments; the data binding unit establishes a mapping relation between the structured label variable and associated data in a system database or item information input by a user; the model storage unit combines the screened XML fragments into a complete XML bid invitation model, and stores the complete XML bid invitation model in a classified manner according to industry categories; a bid invitation file generation unit calls a bid invitation model matched with the item information input by the user, and automatically fills the associated data into a label variable to generate a complete bid invitation XML file; the bidding file generation unit is used for classifying project data filled by a bidder according to requirements and generating bidding XML file data; and the bid evaluation auxiliary unit extracts project data bound with the structured label variables and generates a transverse comparison analysis table.

Embodiments described herein relate to systems and methods for automatically generating content, generating API requests and / or request bodies, structuring user-generated content, and / or generating structured content in collaboration platforms, such as documentation systems, issue tracking systems, project management platforms, and other platforms. The systems and methods described use a network architecture that includes a prompt generation service and a set of one or more purpose-configured large language model instances (LLMs) and / or other trained classifiers or natural language processors used to provide generative responses for content collaboration platforms.

The invention relates to a special effect video generation method and system, and the method comprises the following steps: S1, carrying out video content understanding based on a Vision-Language Model, inputting an original video frame sequence to the Vision-Language Model, and outputting a structured content label and a special effect content candidate list to the Vision-Language Model; s2, performing special effect style injection on the video generation model by adopting a LoRA fine tuning technology so as to realize personalized and content-driven special effect animation generation; and S3, fusing the special effect layer output by the video generation model with the original video frame to generate a final special effect video with visual impact, natural transition sense and dynamic consistency. According to the invention, the video content can be automatically identified and the special effect video conforming to the video content is generated.

The invention provides a standard draft auditing and correcting method and device, electronic equipment and a storage medium, and relates to the technical field of data processing, and the method comprises the steps: obtaining a to-be-audited standard draft, and preprocessing the to-be-audited standard draft to obtain structured content data and structured format data of the to-be-audited standard draft; inputting the structured content data into a pre-trained content correction model to obtain a standard draft marked with to-be-corrected content; wherein the content correction model is obtained through reinforcement learning training based on a large language model; comparing the structured format data with a pre-constructed format knowledge database to obtain a standard draft marked with a to-be-corrected format problem; and re-checking the to-be-corrected content and the to-be-corrected format problem, carrying out content correction on the to-be-corrected content after re-checking, and carrying out format correction on the to-be-corrected format problem to obtain a correct standard draft. The auditing efficiency and accuracy of the standard draft are improved.

The invention relates to the technical field of data processing, and particularly discloses a consistency comparison method and system for multi-modal electronic signed files, and the method comprises the following steps: S1, carrying out the multi-dimensional Hash calculation of a to-be-compared file, and generating a comprehensive Hash consistency score; s2, judging whether the comprehensive hash consistency score reaches a preset threshold value or not: if yes, judging that the comparison files are consistent; if not, cross-modal conjoint analysis is carried out on the text, the image and the structured content of the comparison file through a multi-modal deep learning model, and a consistency prediction score is generated; s3, judging whether the comparison files are consistent or not according to the consistency prediction score and a preset threshold value, and generating a judgment result; by comprehensively applying multi-dimensional hash code analysis and combining and using multi-modal model comparison and covering data of different formats and types, subtle changes of various contents such as texts, images and tables can be detected, so that the high efficiency and accuracy of the electronic signed file are improved.

Embodiments described herein relate to systems and methods for automatically generating content, generating API requests and / or request bodies, structuring user-generated content, and / or generating structured content in collaboration platforms, such as documentation systems, issue tracking systems, project management platforms, and other platforms. The systems and methods described use a network architecture that includes a generative interface panel having multiple automated assistant services. Each assistant service may access a prompt generation service and a set of one or more purpose-configured large language model instances (LLMs) and / or other trained classifiers or natural language processors used to provide generative responses for content collaboration platforms.

The invention discloses a child multi-modal data output method and system, and relates to the technical field of data output. The method comprises the following steps: constructing a semantic chain containing parent interaction requests and historical round input contents, and generating interaction state data reflecting real demands and context changes of parents; then, a synchronous lock mechanism is introduced to schedule a recommended content output queue, synchronous output control data is generated, then semantic label labeling is carried out on key frame actions, adaptive action fragments are screened in combination with infant stage rules, and structured content and interactive prompts are constructed; and finally, dynamic scheduling of multi-modal output contents is realized in combination with interactive prompt data and a synchronous control signal, so that the time sequence coherence, the semantic correlation and the child age adaptability of recommended contents are improved.

The invention relates to the technical field of document processing, and provides a document classification splitting method, device, system and equipment and a storage medium, and the method comprises the following steps: obtaining a PDF format document, and judging whether the PDF format document is in a scanning PDF format; if the document in the PDF format is in a scanning PDF format, analyzing each structured content of the document in the PDF format on the basis of a multi-mode OCR (Optical Character Recognition) engine; if the document in the PDF format is not in the scanning PDF format, analyzing each structured content of the document in the PDF format based on a structured document analysis engine; sorting each structured content into a plurality of document logic units according to context semantics based on a reinforcement learning model; and for each document logic unit, fusing the text feature, the visual feature and the structural feature of the document logic unit, and carrying out classified marking on the document logic unit based on the classification model. The PDF format document can be intelligently and automatically classified and split, the splitting accuracy is high, and the splitting efficiency is high. And the splitting effect is good.

A system and method are disclosed for generating conversational content from human-readable documents. The method includes receiving a document comprising unstructured or semi-structured content and extracting linguistic and layout features using a language model and layout analysis techniques. The document is segmented into atomic content blocks representing discrete semantic units. For at least one content block, a natural language question is generated using a neural model, and a corresponding answer is extracted or synthesized. An optional rephrasing step modifies the surface form of the question or answer while preserving semantic meaning. Each question-answer pair is reviewed using automated or human-in-the-loop mechanisms for accuracy and alignment. Approved content is stored in a structured repository along with metadata supporting traceability and deployment. The system supports enterprise-scale generation of high-quality conversational data for downstream applications such as chatbots, virtual assistants, and retrieval-based AI systems.

The invention relates to the technical field of artificial intelligence, in particular to a video content understanding method and system based on artificial intelligence, and the method comprises the steps: firstly obtaining a video scene unit set which is arranged according to a time sequence of a to-be-understood video and contains scene elements and object behavior information; establishing a semantic behavior association graph of scene element information and object behavior information for each scene unit; generating a hierarchical understanding process containing scene element semantic association analysis and object behavior logic association analysis based on the semantic behavior association graph; dynamically optimizing and adjusting the hierarchical understanding process according to an analysis result; and finally, outputting a structured content understanding result containing scene semantic description and object behavior logic description based on the optimized process, thereby comprehensively, deeply and dynamically understanding the video content.

The invention discloses a file structured information extraction method and device, equipment, a medium and a product, and relates to the technical field of data processing, and the method comprises the following steps: determining a file content type of a to-be-processed file; under the condition of determining that the file content type is the image content file, performing text recognition on the to-be-processed file, and determining a to-be-processed text contained in the to-be-processed file and a text region coordinate corresponding to the to-be-processed text in the to-be-processed file; carrying out structured content entity recognition on the to-be-processed text, and determining structured content entities contained in the to-be-processed text and content entity coordinates respectively corresponding to the structured content entities in the text region coordinates; and constructing content entity relation data among the structured content entities according to the content entity coordinates, and performing structured information extraction on the to-be-processed text according to the content entity relation data to obtain target structured information contained in the to-be-processed file. According to the invention, the accuracy and integrity of structured information extraction can be improved.

The application discloses a kind of extraction methods, device, equipment, medium and product of file structured information, it is related to data processing technical field, comprising: determining the file content type of to-be-processed file;In the case where it is determined that file content type is image content file, to-be-processed file is carried out text recognition, and the text area coordinates of to-be-processed text contained in to-be-processed file and to-be-processed text in to-be-processed file are determined;To-be-processed text is carried out structured content entity identification, and the content entity coordinates of each structured content entity in text area coordinates respectively corresponding to structured content entity contained in to-be-processed text are determined;According to each content entity coordinates, the content entity relationship data between each structured content entity is constructed, and according to content entity relationship data, to-be-processed text is carried out structured information extraction, and the target structured information contained in to-be-processed file is obtained.The application can improve the accuracy and integrity of structured information extraction.

The invention provides a vehicle repair file processing method and related equipment, and the method comprises the steps: receiving a vehicle repair file uploaded by a user, and recognizing the format of the vehicle repair file; converting the automobile repair file into a Markdown format by using a conversion method matched with the format of the automobile repair file to obtain a target automobile repair file; inputting the target automobile repair file into a preset language large model to obtain file content extracted by the language large model; and exporting the file content according to a preset business data format. In the scheme, the automobile repair file format is recognized and uniformly converted into the Markdown format, the problem of complex format analysis of multi-column typesetting, table nesting and image-text mixing is solved, the content is standardized, the standardized file is input into a large language model, the natural language understanding ability of the standardized file is utilized, professional terms are precisely recognized, and the structured content is extracted; the extracted content is exported according to the preset service format, so that unified management of the automobile repair file content is realized, and the data utilization rate is improved.