110 results about "Document structuring" patented technology

Disclosed is a method for customizable schema-guided conversion of plain-text documents, rich-text documents and textual data records to an XML-compatible structured form. The method makes substantial use of element content model definitions from a chosen target XML schema/DTD to optimize, closely guide, and disambiguate element pattern matching and recognition. Highly granular structure can be inferred, in best possible conformance with the schema. One embodiment operates based on a finite state machine derived via recursive aggregation of the schema element content models. Additionally disclosed is a method for automated document structuring within the environment of an XML-enabled wordprocessor application. The method entails using the host's API to perform element pattern search and matching and to apply markup to the document in accordance with the inferred XML structure. A GUI framework integrated in the wordprocessor workspace can be provided for developing and executing document conversion/structuring definitions.

A method and system for classifying semi-structured documents by distinguishing sub-tree structural information as a distinct representative characteristic of a fragment of the document structure identified by a sub-tree node therein. The structural information comprises both an inner structure and an outer structure which individually can be exploited as representative data in a probabilistic classifier for classifying the sub-tree itself or the entire document. Additional representative feature data can also be independently used for classification and comprises the data content of the fragment structurally represented by the sub-tree and additionally with node attributes. The classification values independently generated from each of the different sets of features can then be combined in an assembly classifier to generate an automated classification system.

The invention discloses a topic model based document keyword extraction method and system. The document keyword extraction method comprises the following steps of document information preprocessing, document structure graph construction, document topic distribution extraction, word weight extraction and keyword generation. The document keyword extraction system comprises the following modules: a document information preprocessing module, a document structure graph construction module, a document topic distribution extraction module, a word weight extraction module and a keyword generation module. According to the method and system, extracted keywords are more reasonable and related to a topic of a document more closely; and partial deficiencies in the keyword extraction field at present are overcome, a better document summarization effect is achieved, and a user can conveniently and quickly know an abstract of the document.

The invention relates to a method and a terminal for creating paper document structured data based on a deep learning model. The method comprises the following steps: training a sample set through a preset document; wherein each sample in the document sample set comprises a paper document OCR recognition result and a labeled document corresponding to the paper document OCR recognition result; wherein the labeled document records position information and category information of each key field in the OCR recognition result of the paper document; training a preset first deep learning model by using the training sample set to obtain a second deep learning model; enabling the second deep learning model to analyze a first paper document OCR recognition result to obtain position information and category information of each key field in the first paper document OCR recognition result; and creating a structured document corresponding to the first paper document OCR recognition result accordingto the position information and the category information of each key field in the first paper document OCR recognition result. The accuracy of converting the OCR result of the paper document into thestructured document is improved.

A job model with which an organization model representing an organization structure, a document model representing a document structure, and a work model representing a work procedure are correlated, is stored independent from a service model defining each service. When a service is performed, with reference to the job model corresponding to the service model, a service executing module causes a tool control module to control a tool. Thus, the required service is accomplished.

The invention relates to a document information extraction method and device based on sequence labeling and a learning model. The method comprises the following steps: training at least one sequence labeling algorithm model to obtain at least one offline sequence labeling algorithm model; Determining the accuracy of the annotation information in each of the offline sequence annotation algorithm models, and converting a to-be-processed document into a text document; Obtaining document structure format property information from the to-be-processed document; And inputting the text document and the structural format property information into the offline sequence labeling algorithm model to obtain labeling information corresponding to the document information in the document. According to the method, the key information of the document can be extracted by using the sequence labeling technology. And by using a multi-model fusion technology, different key information in the document can be extracted by using an optimal model. In addition, business rule reasoning and calculation are carried out on a typeface extraction result, and the application range is wider.

Computerized systems and methods are disclosed to generate a document by providing a document structure having one or more seed landmark texts therein, each landmark text including a milestone overview text and a plurality of component texts; from the milestone overview text, generating one or more computer-generated text suggestions to supplement the milestone overview text; combining the milestone overview text with each component text and generating one or more computer-generated component text suggestions; and creating the document by combining the milestone overview, the one or more computer-generated text suggestions, and each component text with corresponding one or more computer-generated component text suggestions.

A document processor includes a parser that parses a document using a grammar having a set of terminal elements for labeling leaves, a set of non terminal elements for labeling nodes, and a set of transformation rules. The parsing generates a parsed document structure including terminal element labels for fragments of the document and a nodes tree linking the terminal element labels and conforming with the transformation rules. An annotator-annotates the document with structural information based on the parsed document structure.

The invention provides an OFD document webpage end browsing method and system, and the method comprises the steps: a browser transmitting an OFD document identification to a server, and the server returning the page structure information of an OFD document to the browser; and the browser grouping the OFD documents according to the received information, generating HTML tags of all groups, and generating HTML tags containing pages under the current group; if the current page is the nth page, the browser querying whether the (n-1)th page, the nth page, the (n + 1)th page and the (n + 2)th page are loaded or not in a browser cache, if yes, not processing, and if not, requesting corresponding page data to be loaded to the server. An asynchronous loading mode is adopted, loading is carried out according to needs, waiting time of a browser end is shortened, an HTML document structure is simplified, rendering pressure of a browser can be reduced, and response speed of the browser is improved.

The invention relates to the field of computer knowledge management. The invention relates to the field of data embedding, in particular to a document structured data embedding method and system. Thesystem comprises a template generator, a document editor, a structured data collector, a data authentication processor, a structured data controller, a template library and a data extraction and conversion interface, the method specifically comprises the following steps of: constructing a document structured framework template; pre-loading into a document editor; editing of the structured data label and the extensible semi-structured data label is completed, the edited document data is extracted and converted into xml structural body data and document attribute fields, the structural body datais embedded into a target format file, and the structured data and the extensible semi-structured data in the structural body data are extracted. By means of the method, the documents can meet the requirements for manual reading, understanding, using and filing, automatic collection and processing of the documents embedded with the structural data can be achieved, and the requirements for the standardization degree and data precision of the documents can be effectively controlled.

The invention provides a document structuring method and device, wherein the method comprises the steps of dividing a to-be-structured document into a plurality of single chapter documents according to a text structure recognition model, calculating the similarity between the chapter title and each template name in the structured template to obtain an adaptive template name, calculating the similarity between the elements corresponding to the adaptive template names and the subordinate statements of corresponding chapter titles to obtain the adaptive statements, and filling the adaptive statements of all the single chapter documents into the corresponding fillable areas in the structured template to obtain the structured document, so that according to the document structuring method and device provided by the invention, the unstructured document can be accurately divided according to the preset structuring template, and the structured document having the corresponding relationship withthe template name and elements can be accurately generated, and accordingly the accuracy of subsequently determining the key points is ensured.

The invention discloses a document structuration organizing method and device. The document structuration organizing method includes the steps of obtaining a theme framework of a hierarchical structure, forming a searching condition through a theme text in the theme framework, carrying out searching in a preset document set with the searching condition, and adding a document into a corresponding theme document set in the theme framework according to the matching condition of the searching result and the searching condition. Compared with the prior art, the technical scheme of the document structuration organizing method and device can be used for automatically building proper classification systems according to different knowledge fields; as the theme framework is built with mature expert knowledge, inner links of classifications can be well reflected, and a user can conveniently read a large number of texts in a systematized mode.

One embodiment of the invention discloses a document online editing system and method based on authority control, and the system comprises a document management module which is used for storing document templates and all documents edited by users, and setting authority levels corresponding to the document template and the documents; a personnel management module used for dividing authority levelsof the users; a document structuralization module used for performing structuralization division on the document templates or the documents; an authority module used for distributing and structuring the divided document templates or documents to the users according to the authority levels of the document modules or documents and the authority levels of the users; and an online editing module usedfor carrying out online editing on the document templates or the documents by the users and storing the content.

The invention provides a universal document recognition method, which comprises the following steps of: obtaining text information of one or more text fields in a document, the text information comprising text content and a text bounding box; obtaining category information in one-to-one correspondence with one or more text fields in the document, wherein the category information at least comprises a primary key field category Key and a value field category Value; obtaining a connection relationship between the character field of which the category is Key and other character fields; and on the basis of the connection relationship, obtaining a Value-class text field connected or disconnected with a Key-class text field and/or a Key-class text field as structured content corresponding to the Key-class text field, determining class information and text information of the structured content, and completing identification of the document. Meanwhile, the invention provides a corresponding system, a terminal and a storage medium. According to the method and the device, the accuracy and universality of document structured content identification are improved.

The invention relates to a structuring method of a continuous page format document. Characters, fonts, word sizes, positions and other information in a continuous page format document are extracted page by page; page headers and page feet are recognized and removed through preprocessing; footnotes are identified and segmented; and the remaining multiple pages of text contents and footnote contentsare respectively merged into a virtual page, layout analysis, text block merging, column dividing and table processing are carried out on the virtual page to generate a text block table, and outlineextraction is carried out according to rules by utilizing the characteristics of numbers, font sizes, alignment and the like of the text block table so as to restore the logic structure of the whole file. By the adoption of the method, interference texts such as page headers, page feet and footnotes can be effectively removed, the column reading sequence is guaranteed, the structural correctness of the texts is greatly improved, the workload of manual correction is reduced, and the efficiency is improved.

The invention provides a judgment document structuring method and device. The method comprises the steps of firstly, extracting a block text in a to-be-processed judgment document by utilizing a firstextraction template, the method comprises the steps of obtaining a first structured text according to a preset feature expression format, then extracting from a specified block text of the first structured text by utilizing a second extraction template to obtain a first sub-structured text, and converting a sub-block text of the first sub-structured text into a text with the preset feature expression format to obtain a second sub-structured text. And finally, updating the corresponding content in the first structured text by utilizing the second sub-structured text to obtain a second structured text. Therefore, according to the judgment document structuring method provided by the invention, the first structuralized text can be further extracted, and meanwhile, the extracted text is converted into the text format more conforming to the display structure, so that a user can quickly locate the required content through browsing.