58 results about "Formatted text" patented technology

The invention relates to an engineering document index consistency proofreading method and system based on a multi-modal large model, and the method comprises the steps: Q1. OCR detection and recognition: carrying out the optical character recognition and format analysis of a source document, converting an uploaded PDF document into a processable text message in a Markdown format, and carrying out the format discrimination of a table, a formula and a plain text; and Q2, table and formula processing: adopting a hierarchical processing strategy, intelligently selecting an optimal processing mode according to the complexity of the table, and converting table information into a descriptive long text through a language large model and cue words. According to the method, accurate, reliable and efficient document index checking service can be provided for a user, the quality and efficiency of professional document processing are remarkably improved, the efficiency and quality of knowledge graph construction are remarkably improved, a knowledge verification system capable of being evolved continuously is established, and the method is suitable for popularization and application. And a reliable technical support is provided for knowledge management and professional decision-making in a complex field.

The invention provides a vertical field data construction method based on a large model, which belongs to the technical field of data processing and artificial intelligence, and comprises the following steps: converting a vertical field source document into an intermediate format text, and segmenting the intermediate format text into a plurality of text blocks; inputting the text blocks into a pre-trained generative language model, guiding the pre-trained generative language model according to pre-designed cue words to generate a plurality of candidate questions according to the content of the text blocks, and performing preliminary screening and fine screening on each candidate question to obtain a question set; pre-defining a mode of a knowledge graph according to field characteristics of the vertical field, processing all text blocks based on an information extraction model, and constructing a field knowledge graph; and performing local context retrieval on each final question in the question set based on the text block of the question source, performing global knowledge retrieval based on the domain knowledge graph, and generating a final answer and a final thinking chain. The method is suitable for different vertical fields, the data quality can be effectively improved, and the problem generation accuracy is guaranteed.

The invention discloses an alloy field-oriented text and table double-track collaborative data extraction method and system. The method comprises the following steps of: obtaining an alloy related document DOI; taking the DOI as an index to obtain a full-text literature and storing the full-text literature in a JSON format; performing document screening based on an LDA topic distribution model and establishing a target topic document library; preprocessing the unstructured table, and obtaining structured table data by using a large language model; performing automatic text segment division on the JSON format text through rule matching analysis; and sorting the text segments by using a large language model to generate semi-structured text data, fusing and normalizing the text and table data, and outputting a component-process-organization-performance-strengthening mechanism alloy data chain. According to the method, through a double-track collaborative data extraction mechanism, the problems of multi-source heterogeneity, format fragments, information islands, semantic layering and the like of material subject data are effectively solved, structured treatment of literature data in the alloy field is achieved, and a unified technical path is provided for constructing a high-quality alloy database.

The invention discloses a plant protection field literature information batch structured extraction method based on an AI large model, and belongs to the technical field of computer data processing and artificial intelligence application. According to the method, a PDF format literature is converted into a Markdown format text through a PDF literature self-adaptive preprocessing module and a Markdown conversion module; then, a double-strategy self-adaptive AI extraction module is adopted, different modes are adopted for processing according to a text length threshold value, and JSON data are extracted in combination with a JSON format data restoration strategy; then, the CPU intensive conversion task and the I / O intensive AI analysis task are processed in parallel through a two-stage parallel scheduling module, and a structured database file is generated through aggregation according to a predefined mapping rule through a multi-dimensional aggregation export module. According to the method, end-to-end automation from literature acquisition to structured data output is realized, and the problem of low extraction efficiency of manual literature reading information is solved.

The invention relates to the technical field of passenger service, and discloses a construction method and device of a dynamic extension word bank, equipment and a medium. The method comprises the following steps: acquiring multi-source heterogeneous original knowledge data related to civil aviation passenger service, and converting the multi-source heterogeneous original knowledge data into a standard format text; processing the unstructured data in the standard format text based on the adaptive word segmentation model and the stop word list to obtain a plurality of candidate words; performing multi-dimensional corpus feature quantitative analysis on each candidate word to determine candidate keywords; and performing similarity calculation based on the entity word segmentation and the candidate keywords, determining effective candidate keywords, and adding the effective candidate keywords into the dynamic expansion word bank. By means of the method and device, the technical problems that in the prior art, a word bank used by a civil aviation service system is usually based on a static vocabulary or depends on manual compiling and updating, the static word bank cannot be updated in real time, the characteristics of the civil aviation field cannot be flexibly handled, and the maintenance cost is high due to manual updating and maintenance are solved.

The invention discloses an intelligent cue word generation evaluation method and system based on multi-component collaboration, and relates to the technical field of artificial intelligence and natural language processing. The method comprises the following steps: acquiring a multi-format text, converting the multi-format text into an input-output pair, and generating a plurality of candidate cue words; after determining a communication mode according to the text form, standardizing cue words according to the structured template of each large language model; calling each platform to generate answer analysis and unify formats, and extracting target contents by utilizing regularization; and carrying out multi-mode evaluation on the candidate cue words, selecting an optimal cue word, and outputting a structured evaluation result and an optimization suggestion based on multiple indexes. According to the method, full-process automatic processing of prompt word generation, optimization and evaluation is achieved, various model platforms, data sets, algorithms and evaluation indexes are supported, and good universality and expansibility are achieved.

The invention provides an industrial internet network intrusion detection method based on a pre-trained large language model, and the method comprises the steps: carrying out the data preprocessing of original network flow data through protocol self-adaptive flow aggregation and session segmentation, feature screening and feature coding; constructing a stream format text data set used for training a generation model GPT-2 and a packet level classification text-label data set used for training a classification model DistilBERT; then fine tuning training is carried out on the generation model GPT-2 and the classification model DistilBERT; then calling a trained generation model GPT-2 to generate a traffic sequence, obtaining a prediction data packet, calling a trained classification model DistilBERT, performing anomaly judgment on sequence data in the prediction data packet one by one, and outputting a classification result of anomaly judgment; the active intrusion detection of first generation and then discrimination is realized. According to the method, prediction can be made before real attack traffic arrives, and network attacks are prevented.

The present invention belongs to the technical field of text processing, and relates to an intelligent extraction method and system for an input text containing a mathematical formula. The method comprises: 1) performing format determination, conversion and preprocessing on an input text; 2) performing angle correction on the preprocessed image-formatted text; 3) performing formula detection; 4) performing layout analysis; 5) for inline formulas, according to a formula detection box, determining whether a corrected OCR detection box contains an inline formula, and splitting the OCR detection box containing the inline formula, so as to obtain a text-only OCR detection box; 6) performing formula recognition to obtain a formula recognition result; 7) performing text recognition to obtain a text recognition result; and 8) on the basis of a layout analysis box and a layout category thereof, performing same-line detection box determination and merging on the formula recognition result and the text recognition result, so as to obtain an extraction result for the input text. The present invention can effectively improve the extraction efficiency and accuracy for input texts containing mathematical formulas.

The invention relates to the technical field of aeronautical text data processing, and discloses an aeronautical text content cleaning and labeling method, system, device and medium wherein the method comprises: noise filtering: identifying and removing noise in an aeronautical text in combination with static cleaning and a general large model; format standardization: converting the aviation text after noise removal into a standardized format text; duplicate removal and error correction: detecting duplicate contents based on a hash algorithm, and correcting spelling errors and grammar errors based on a general large model to obtain an aviation text subjected to duplicate removal and error correction; entity identification: key entities are extracted based on the general large model, and the extracted key entities are labeled; active learning: screening high-value samples in the marked key entities based on an uncertainty query strategy; and dynamic optimization: performing verification and iterative optimization on the marking result in combination with the aviation knowledge base. According to the method, the automation level, the labeling accuracy and the system self-adaptive capability of aviation text processing can be remarkably improved.

The embodiment of the invention relates to a contract information extraction method and device, equipment and a medium. The method comprises the steps of obtaining a to-be-processed clause text in a to-be-processed contract text; responding to the to-be-processed clause text as a target clause text, obtaining a prompt word template corresponding to the to-be-processed clause text, and setting a corresponding prompt identifier for the prompt word template corresponding to the to-be-processed clause text to obtain a target prompt word template; and performing information extraction on the to-be-processed term text based on the target cue word template through a preset large model to obtain target format text information so as to determine contract information corresponding to the to-be-processed contract text. Therefore, the key information of each clause text can be quickly and accurately extracted through the large model, the accurate information of the whole contract text can be obtained, the prompt identifier is added for the specific clause to improve the recognition accuracy, and the contract information recognition efficiency and effect are further improved; therefore, the contract-related business processing efficiency is improved, and the business error risk is reduced.

A system for adaptive text rendering includes an editor, a context analyzer, an adaptive text generator, and a feedback and learning engine. The editor renders a text box on a digital canvas and receives user input via the text box. The context analyzer extracts contextual information from digital content associated with the digital canvas. The adaptive text generator uses the user input, text box dimensions, and contextual information to direct an artificial intelligence (AI) model to generate text. It then formats the generated text to fit within the text box based on one or more fit criteria. The feedback and learning engine captures and evaluates user feedback related to the formatted text and generates tuning adjustments to refine the adaptive text generator or the AI model.

In some implementations, a device may identify a form field, of a form, that is to be filled with text. The device may determine a formatting for the text that is to be used for filling the form field. The formatting for the text may be determined based on content that is indicative of the formatting that is to be used for filling the form field, or information relating to at least one previous filling of the form field that is associated with a successful submission of the form. The device may modify the text in accordance with the formatting that is determined to obtain formatted text. The device may cause filling of the form field with the formatted text.

The application discloses a ship structure strength calculation formula fine-grained knowledge extraction method, which faces a ship structure strength calculation scene and comprises the following steps: generating a specified format text file by analyzing a ship structure strength calculation guide PDF; constructing a ship structure strength calculation formula fine-grained extraction large model; obtaining text-level full-quantity triple by adopting a general ontology model guided text-level full-quantity triple extraction method and a semantic-based triple edge relationship supplementing and correcting method; perfecting the ontology model by adopting an ontology model generation and attribute expansion method based on rule filtering and hierarchical clustering; formulating attribute value text description by adopting a triple snowflake type expansion method based on attribute semantic depth mining; and specifying attribute value reference description by adopting a triple supplementing method based on reference association expansion, so as to obtain formula-level full-quantity triple, thereby constructing a calculation formula graph and realizing the structured management of the calculation formula.

Electronic system and method for assisting a civil aircraft operator in decision-making with the development of aeronautical indicator(s), civil aircraft and associated computer program. The present invention relates to an electronic system (15) for assisting a civil aircraft operator in decision-making (10), comprising: - an electronic device (18) for displaying information; - an electronic device (20) for developing aeronautical indicators, comprising: + a module (30) for acquiring at least one aeronautical information message comprising a header and a useful part, the useful part including several data fields, including a free-format text field, called the free field;+ a module (32) for calculating several aeronautical indicators for each aeronautical information message via the application of an artificial intelligence algorithm to said message, the artificial intelligence algorithm receiving the free field as input and delivering the indicators as output, these being distinct from the data contained in said message; + a module (34) for displaying a rendering of the aeronautical indicators. Figure for the abbreviation: Figure 1;

The invention belongs to the field of natural language processing and large language models, and particularly discloses an intelligent question and answer method and system for a document in the field of water taking permission, and the method comprises the steps: analyzing a water taking permission document through layout recognition, and obtaining a json format text; performing knowledge extraction on the text, namely identifying a paragraph main entity through a paragraph main entity dual-channel detection and entity identification iterative training method, complementing the content of an indication pronoun in the text through long-distance anaphora resolution based on an elastic sliding window, and guiding a large language model to extract a triple by using knowledge extraction Prompt, data cleaning is carried out on the data; constructing a vector database index based on the cleaned triples, and when a user question is received, retrieving candidate triples related to the user question by using the vector database index; and inputting the retrieved candidate triples into the large language model to generate answers to the user questions. According to the method, the knowledge can be efficiently and accurately extracted and retrieved from the water taking permission document.

The embodiment of the invention discloses a machine-readable building engineering standard digital processing method and a machine-readable building engineering standard digital processing device. A specific embodiment of the method comprises the steps of generating text sequence information according to a first preset processing mode; generating layout information and bibliography and reference relation information according to preset layout annotation information, the layout level identification model and preset bibliography annotation information; text information is generated according to preset text labeling information and a paragraph extraction model; according to a pre-trained formula identification model, generating special format text information; determining the text sequence information, the layout information, the bibliography and reference relation information, the text information and the special format text information as construction standard control information; and generating control parameter information according to the construction standard control information, and controlling the construction robot to perform construction processing according to the control parameter information. According to the embodiment, the accuracy of obtaining the building engineering standard information is improved, the construction time consumption is shortened, and the waste of equipment resources is reduced.

The present disclosure provides a presentation document parsing method and system, wherein the presentation document parsing method comprises: obtaining recognition results of all pages of a presentation document; wherein the recognition results comprise intermediate state JSON data and Markdown format text content of all pages; obtaining a structured information extraction outline of the presentation document according to a user intention and the recognition results; determining key pages of the presentation document corresponding to the structured information extraction outline; inputting original page images, text recognition results and chart structure codes of the obtained key pages into a visual large model to output a presentation document structured parsing result conforming to the user intention. The present disclosure generates a structured information extraction outline of the presentation document according to the user intention, so that the user does not need to know the structure and content of the presentation document in advance, and the parsing path of the presentation document can be automatically planned, greatly reducing the use threshold.

The invention provides a Word document generation method and system, electronic equipment and a storage medium. The method comprises the following steps: displaying a Web page containing a text editing area; obtaining input content and format requirements in the text editing area; judging whether the input content contains a structure identifier or not; if not, calling a semantic recognition model to perform structured analysis on the input content; if yes, performing hierarchical structure analysis on the input content according to a regularization rule and / or calling a semantic recognition model to perform structured analysis on the input content; and adjusting the input content according to the analysis result and the format requirement, and generating a Word document. Word document generation does not depend on a template, a fixed template does not need to be designed in advance, a text of a fixed structure does not need to be provided according to the template, a user can obtain the standard Word document by submitting the text of the free format through the Web page, operation is convenient and fast, universality is high, and flexibility is high.

This application relates to a method, apparatus, and storage medium for displaying text to be displayed. The method includes: upon acquiring the text to be displayed, acquiring the global offset of the target text within the text to be displayed that requires formatting adjustment; determining the global character range of each slice in the slicing results of the text to be displayed; determining, based on the comparison result between the global character range and the global offset, a target slice containing the character to be adjusted, and determining the local offset of the character to be adjusted within its respective target slice; and during the streaming display of the target slice of the text to be displayed, adjusting the format of the character to be adjusted corresponding to the local offset within the target slice before displaying it. This application solves the technical problem that formatted text cannot be displayed when displaying long text output by LLM.

The present invention relates to a computer-implemented system (100) and a computer-implemented method for generating datasets (3) representing traffic scenarios, which are to be used for training and / or testing automated driving (AD) functions. The system (100) comprises one or more processors and a memory that stores one or more programs configured for execution by the one or more processors. The programs comprise at least one first large-language model (LLM) and / or vision-language model (VLM), which are trained on at least formatted text descriptions of traffic scenarios and on natural language to perform a task specified by a prompt. Furthermore, the programs include instructions for: • Transforming an initial data set (1) into a formatted text description of a corresponding real-world traffic scenario, • Generating an initial prompt (11) as input for the initial LLM or VLM acting as a modification agent (10), wherein the initial prompt (11) includes the formatted text description of the real traffic scenario and a user specification of a desired modification of the real traffic scenario, • Applying the first prompt to the modification agent (10) and receiving a modified formatted text description of a modified traffic scenario as output (12), and • Transforming the modified formatted text description into a corresponding data set (3) that represents the modified traffic scenario.

A computer implemented system and method for generating data sets representing traffic scenarios to be used for training and / or testing automated driving functions are disclosed. The system includes one or more processors and a memory that stores one or more programs that are configured to be executed by the one or more processors. The programs include at least one first Large Language Model (LLM) and / or Vision Language Model (VLM) being trained at least on formatted text descriptions of traffic scenarios and on natural language to perform a task given a prompt. Further, the programs include instructions to (i) transform an initial data set into a formatted text description of a corresponding real traffic scenario, (ii) construct a first prompt as input for the first LLM or VLM acting as modifier agent, wherein the first prompt includes the formatted text description of the real traffic scenario and a user specification of a wanted modification of the real traffic scenario, (iii) apply the first prompt to the modifier agent and obtain a modified formatted text description of a modified traffic scenario as output, and (iv) transform the modified formatted text description into a corresponding data set representing the modified traffic scenario.

The invention discloses a knowledge graph-based learning path planning method, which comprises the following steps of: acquiring learning behavior data of a learner, and preprocessing audio data in the learning behavior data into formatted text data; analyzing the preprocessed text data, and performing entity extraction and relationship extraction to obtain a head entity, a relationship and a tail entity; the head entity, the relation and the tail entity form a triple, and an English knowledge graph of the student is formed through the triple to represent the oral English learning condition of the student; performing interactive fusion on entities and relation embedding of the English knowledge graph, and performing training by using an FIMA-GNN model to respectively obtain updated entities and relation embedding; and embedding based on the updated entities and relationships to obtain a target knowledge graph, and reasoning according to the target knowledge graph to generate a personalized learning path. According to the method, multi-modal data acquisition and analysis of oral English learning behaviors of learners can be realized, and personalized learning content suggestions are generated.

The application provides a large model-based vertical field data construction method, and belongs to the technical fields of data processing and artificial intelligence, and comprises the following steps: converting a vertical field source document into an intermediate format text and dividing the intermediate format text into multiple text blocks; inputting the text blocks into a pre-trained generative language model, guiding the pre-trained generative language model to generate a plurality of candidate questions according to the contents of the text blocks according to a pre-designed prompt word, and performing preliminary screening and fine screening on each candidate question to obtain a question set; predefining a mode of a knowledge graph according to the field characteristics of the vertical field, processing all the text blocks based on an information extraction model, and constructing a field knowledge graph; and performing local context retrieval based on the text blocks of the source of each final question in the question set, performing global knowledge retrieval based on the field knowledge graph, and generating a final answer and a final thinking chain. The application is suitable for different vertical fields, and can effectively improve the quality of data and ensure the accuracy of question generation.

The invention discloses a meteorological data format conversion method based on data translation, and relates to the technical field of data processing driven by artificial intelligence, and the method comprises the following steps: carrying out zoning space cutting and time window alignment on multi-source meteorological data to generate standardized input; analyzing the standardized data into time tags and geographic tags to form structured semantic description; and constructing cue words according to the structured tag to drive the large language model to output a fixed format text. According to the method, standardization of model semantic input is achieved through semantic structure modeling; and on the basis of a label-driven cue word construction and term specification mechanism, the professional output capability of a large language model in meteorological services is enhanced. The risk of model illusion and semantic deviation is effectively reduced, and the accuracy and service adaptability of automatic meteorological text generation are improved.

This application discloses a method and apparatus for extracting information from formatted text, relating to the fields of information technology and artificial intelligence technology, which helps to improve the accuracy of information extraction from formatted text. The method includes: first, determining the text blocks belonging to the target category in the formatted text to be extracted; second, identifying the text blocks belonging to the target category in the formatted text based on the feature information at the text block granularity; and third, outputting the identifiers of the text blocks belonging to the target category in the formatted text.

The application discloses a meteorological data format conversion method based on data translation, relates to the technical field of data processing driven by artificial intelligence, and comprises the following steps: carrying out zoning space clipping and time window alignment on multi-source meteorological data to generate standardized input; analyzing the standardized data into structured semantic description constituted by time labels and geographical labels; and constructing a prompt word driven by the structured labels to output a fixed format text by a large language model. The method disclosed by the application realizes the standardization of model semantic input through semantic structure modeling; the construction of the prompt word driven by the labels and the term specification mechanism enhance the professional output capability of the large language model in meteorological services. Not only the risk of model illusion and semantic deviation is effectively reduced, but also the accuracy and business adaptability of automatic meteorological text generation are improved.

The embodiment of the invention provides a data processing method and device suitable for retrieval enhancement generation, various documents can be structured into Markdown format texts, and therefore the method and device can be suitable for various slicing modes and can be suitable for long texts. Specifically, structural information is extracted from a text through a large language model to obtain initial structural information of a full text, and then the document structural information of the full text is optimized and finely distinguished by the large language model to obtain corrected document structural information, for example, the corrected document structural information is recorded as target structural information. And mapping the target structure information to a corresponding position of the initial text to obtain a text with a fine structure for performing document slicing in various slicing modes of a conventional technology. Therefore, the illusion risk of a large language model can be reduced, and the cost and processing time consumption are reduced.

A computer-implemented system and method for generating a data set representing a traffic scene for training and / or testing automated driving (AD) functions. The system includes a processor and a memory storing programs executed by the processor. The program includes a first large language model and / or visual language model trained in at least a formatted textual description of the traffic scene and a natural language to perform a task when a prompt is given. The program includes instructions to transform an initial data set into a formatted textual description of a real traffic scene; constructing a first cue as an input for the LLM or VLM acting as a modifier agent, the first cue including a formatted textual description of the real traffic scene and a user specification of a desired modification of the real traffic scene; applying the first cue to the modifier agent and obtaining the modified traffic scene and formatted text description as output; the modified formatted text description is transformed into a corresponding data set representing the modified traffic scene.

This invention provides a method for automatically formatting text boxes in architectural drawings, comprising: Step 1, acquiring all text boxes to be automatically formatted and their coordinate information; Step 2, calculating the total area of ​​the overlapping region of all text boxes based on the coordinate information of the text boxes; Step 3, when the total area of ​​the overlapping region of all text boxes is not 0, determining the text box with the largest overlapping area with other text boxes; Step 4, moving the text box up, down, left, and right by a preset distance, selecting the movement action that minimizes the overlapping area with other text boxes after the movement, and executing the movement action; Step 5, repeating steps 2 to 4 until a predetermined number of repetitions is reached.

The invention provides a multi-modal report automatic generation method and system based on small-scale LLM and RAG technologies, aiming at solving the problems that technical report compilation in the fields of tunnel engineering and the like depends on manpower, a general model is insufficient in specialty, the multi-format processing capacity is weak, the deployment cost is high and the like. The method comprises the steps of multi-format text extraction and path reservation, domain knowledge driven outline generation, RAG-based content optimization and recombination and report assembly and output. According to the method, full-process automation of the multi-modal report is realized, the generation efficiency and specialty are improved, and the deployment cost and the data security risk are reduced.